Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.6381. Min Act: -0.1700
Data Index: 6724205 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.6381. Min Act: -0.1700
Data Index: 402101 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.6068. Min Act: -0.1700
Data Index: 2064299 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.5756. Min Act: -0.1700
Data Index: 5603275 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.5443. Min Act: -0.1700
Data Index: 4412781 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.5131. Min Act: -0.1700
Data Index: 4831829 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4818. Min Act: -0.1700
Data Index: 4486624 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.5131. Min Act: -0.1700
Data Index: 2835645 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4506. Min Act: -0.1700
Data Index: 8389126 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4818. Min Act: -0.1700
Data Index: 2677759 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4818. Min Act: -0.1700
Data Index: 6005017 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4506. Min Act: -0.1700
Data Index: 5988125 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4506. Min Act: -0.1700
Data Index: 6788024 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4506. Min Act: -0.1700
Data Index: 3698043 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4193. Min Act: -0.1700
Data Index: 3689728 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4506. Min Act: -0.1700
Data Index: 1505387 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4193. Min Act: -0.1700
Data Index: 3337194 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4193. Min Act: -0.1700
Data Index: 5396709 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.4193. Min Act: -0.1700
Data Index: 2930023 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6381. Min Range: -4.6381
Max Act: 4.3881. Min Act: -0.1700
Data Index: 4864678 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19