Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 278 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.8939. Min Act: -0.1700
Data Index: 4727927 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.8939. Min Act: -0.1700
Data Index: 3843262 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.8463. Min Act: -0.1700
Data Index: 5236429 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.8463. Min Act: -0.1700
Data Index: 1203983 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.8304. Min Act: -0.1700
Data Index: 4077210 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.8145. Min Act: -0.1700
Data Index: 8182220 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7826. Min Act: -0.1700
Data Index: 2265614 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7985. Min Act: -0.1700
Data Index: 5405071 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7985. Min Act: -0.1700
Data Index: 379428 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7507. Min Act: -0.1700
Data Index: 5247401 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7347. Min Act: -0.1700
Data Index: 1543044 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7347. Min Act: -0.1700
Data Index: 4432857 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7188. Min Act: -0.1700
Data Index: 5994816 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7028. Min Act: -0.1700
Data Index: 5294773 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7188. Min Act: -0.1700
Data Index: 6652004 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7028. Min Act: -0.1700
Data Index: 7883876 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7188. Min Act: -0.1700
Data Index: 5378054 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7028. Min Act: -0.1700
Data Index: 8396724 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.6868. Min Act: -0.1700
Data Index: 3784687 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8939. Min Range: -2.8939
Max Act: 2.7188. Min Act: -0.1700
Data Index: 4530496 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19