Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0672. Min Range: -12.0672
Max Act: 12.0672. Min Act: -0.1700
Data Index: 6274360 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0672. Min Range: -12.0672
Max Act: 12.0047. Min Act: -0.1700
Data Index: 5667832 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.8797. Min Act: -0.1700
Data Index: 8739755 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.6922. Min Act: -0.1700
Data Index: 4072033 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.6297. Min Act: -0.1700
Data Index: 2267577 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.5047. Min Act: -0.1700
Data Index: 6237602 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.4422. Min Act: -0.1700
Data Index: 6566205 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.3797. Min Act: -0.1700
Data Index: 2520071 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.3797. Min Act: -0.1700
Data Index: 1518617 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.3797. Min Act: -0.1700
Data Index: 2957384 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.2547. Min Act: -0.1700
Data Index: 113873 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.1922. Min Act: -0.1700
Data Index: 8765879 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.2547. Min Act: -0.1700
Data Index: 8384684 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.2547. Min Act: -0.1700
Data Index: 5146499 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.2547. Min Act: -0.1700
Data Index: 8316024 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.1922. Min Act: -0.1700
Data Index: 2123170 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.1922. Min Act: -0.1700
Data Index: 6642621 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.1922. Min Act: -0.1700
Data Index: 2900144 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.1922. Min Act: -0.1700
Data Index: 325457 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0672. Min Range: -12.0672
Max Act: 11.1297. Min Act: -0.1700
Data Index: 2789376 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19