Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.7802. Min Act: -0.1700
Data Index: 3967203 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.7802. Min Act: -0.1700
Data Index: 7055568 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.5302. Min Act: -0.1700
Data Index: 2466061 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.4052. Min Act: -0.1700
Data Index: 3099831 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.4052. Min Act: -0.1700
Data Index: 7380730 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.4052. Min Act: -0.1700
Data Index: 5236632 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.2802. Min Act: -0.1700
Data Index: 5870520 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.2802. Min Act: -0.1700
Data Index: 8593997 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.2177. Min Act: -0.1700
Data Index: 549627 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.2177. Min Act: -0.1700
Data Index: 7349911 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.1552. Min Act: -0.1700
Data Index: 7447891 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0927. Min Act: -0.1700
Data Index: 4198276 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0927. Min Act: -0.1700
Data Index: 7359103 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0927. Min Act: -0.1700
Data Index: 1114896 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0302. Min Act: -0.1700
Data Index: 6096636 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0302. Min Act: -0.1700
Data Index: 332493 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0302. Min Act: -0.1700
Data Index: 878995 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0302. Min Act: -0.1700
Data Index: 4018188 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7802. Min Range: -8.7802
Max Act: 8.0302. Min Act: -0.1700
Data Index: 3493649 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7802. Min Range: -8.7802
Max Act: 7.9677. Min Act: -0.1700
Data Index: 415271 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19