Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1187 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.8989. Min Act: -0.1700
Data Index: 2326747 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.5239. Min Act: -0.1700
Data Index: 2045112 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.3989. Min Act: -0.1700
Data Index: 1938745 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.3052. Min Act: -0.1700
Data Index: 6160028 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.2739. Min Act: -0.1700
Data Index: 6509104 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.2114. Min Act: -0.1700
Data Index: 667421 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.2114. Min Act: -0.1700
Data Index: 48534 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.2114. Min Act: -0.1700
Data Index: 7261815 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1802. Min Act: -0.1700
Data Index: 1657820 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1802. Min Act: -0.1700
Data Index: 2113665 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 3448481 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 4380692 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 2809261 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 6690346 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1177. Min Act: -0.1700
Data Index: 2334747 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.1177. Min Act: -0.1700
Data Index: 8705366 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 5124297 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 3390333 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1657816 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8989. Min Range: -6.8989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1899193 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19