Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.1320. Min Act: -0.1700
Data Index: 6188805 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0383. Min Act: -0.1700
Data Index: 2889370 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0695. Min Act: -0.1700
Data Index: 3112048 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 4937097 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0383. Min Act: -0.1700
Data Index: 2731091 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0383. Min Act: -0.1700
Data Index: 6015392 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0383. Min Act: -0.1700
Data Index: 7043061 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 3810503 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0383. Min Act: -0.1700
Data Index: 5895961 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 47985 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 8597534 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 3875113 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 367309 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1320. Min Range: -4.1320
Max Act: 3.9757. Min Act: -0.1700
Data Index: 4119686 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1320. Min Range: -4.1320
Max Act: 3.9757. Min Act: -0.1700
Data Index: 457826 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1320. Min Range: -4.1320
Max Act: 3.9445. Min Act: -0.1700
Data Index: 7917303 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1320. Min Range: -4.1320
Max Act: 3.9757. Min Act: -0.1700
Data Index: 7133943 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1320. Min Range: -4.1320
Max Act: 4.0070. Min Act: -0.1700
Data Index: 170958 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1320. Min Range: -4.1320
Max Act: 3.9757. Min Act: -0.1700
Data Index: 5681478 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1320. Min Range: -4.1320
Max Act: 3.9445. Min Act: -0.1700
Data Index: 3914266 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19