Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 988 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.5587. Min Act: -0.1700
Data Index: 8770287 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.5587. Min Act: -0.1700
Data Index: 1121733 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.5430. Min Act: -0.1700
Data Index: 1357391 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.5430. Min Act: -0.1700
Data Index: 3013351 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4960. Min Act: -0.1700
Data Index: 3013350 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4334. Min Act: -0.1700
Data Index: 7174095 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4334. Min Act: -0.1700
Data Index: 5016335 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4334. Min Act: -0.1700
Data Index: 5219178 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4177. Min Act: -0.1700
Data Index: 8276906 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4020. Min Act: -0.1700
Data Index: 3477246 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4020. Min Act: -0.1700
Data Index: 3176046 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4020. Min Act: -0.1700
Data Index: 4533715 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3863. Min Act: -0.1700
Data Index: 1410766 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3863. Min Act: -0.1700
Data Index: 4731847 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3863. Min Act: -0.1700
Data Index: 1495023 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3707. Min Act: -0.1700
Data Index: 6312836 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.4020. Min Act: -0.1700
Data Index: 2261271 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3393. Min Act: -0.1700
Data Index: 7811113 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3707. Min Act: -0.1700
Data Index: 1504360 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5587. Min Range: -3.5587
Max Act: 3.3393. Min Act: -0.1700
Data Index: 6690857 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19