Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.4921. Min Act: -0.1700
Data Index: 5873727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.4609. Min Act: -0.1700
Data Index: 351034 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.4296. Min Act: -0.1700
Data Index: 20656 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3984. Min Act: -0.1700
Data Index: 895588 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3984. Min Act: -0.1700
Data Index: 5487625 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3671. Min Act: -0.1700
Data Index: 2381616 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3359. Min Act: -0.1700
Data Index: 1499040 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3046. Min Act: -0.1700
Data Index: 4883385 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3359. Min Act: -0.1700
Data Index: 2954934 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3046. Min Act: -0.1700
Data Index: 2183607 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3046. Min Act: -0.1700
Data Index: 2530011 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.3046. Min Act: -0.1700
Data Index: 8458476 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2734. Min Act: -0.1700
Data Index: 161591 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2734. Min Act: -0.1700
Data Index: 8575635 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2734. Min Act: -0.1700
Data Index: 17966 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2734. Min Act: -0.1700
Data Index: 842908 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2109. Min Act: -0.1700
Data Index: 1300517 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2421. Min Act: -0.1700
Data Index: 1903105 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2421. Min Act: -0.1700
Data Index: 4324524 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.2421. Min Act: -0.1700
Data Index: 7394506 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19