Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4951 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.6518. Min Act: -0.1700
Data Index: 1289560 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.5893. Min Act: -0.1700
Data Index: 2360883 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.5893. Min Act: -0.1700
Data Index: 4781123 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.4955. Min Act: -0.1700
Data Index: 2284014 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.4643. Min Act: -0.1700
Data Index: 2412859 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.4018. Min Act: -0.1700
Data Index: 3578302 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.4018. Min Act: -0.1700
Data Index: 3671953 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.4018. Min Act: -0.1700
Data Index: 4430166 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.3393. Min Act: -0.1700
Data Index: 8729935 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.3705. Min Act: -0.1700
Data Index: 3761614 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.3705. Min Act: -0.1700
Data Index: 7794580 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.3393. Min Act: -0.1700
Data Index: 2722700 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.3080. Min Act: -0.1700
Data Index: 3786697 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.3080. Min Act: -0.1700
Data Index: 836652 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.2768. Min Act: -0.1700
Data Index: 7355582 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.2768. Min Act: -0.1700
Data Index: 7308159 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.2768. Min Act: -0.1700
Data Index: 3420903 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.2455. Min Act: -0.1700
Data Index: 4732259 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.2455. Min Act: -0.1700
Data Index: 5304722 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6518. Min Range: -7.6518
Max Act: 7.2455. Min Act: -0.1700
Data Index: 6446747 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19