Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 563 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4242. Min Range: -6.4242
Max Act: 6.4242. Min Act: -0.1700
Data Index: 5943640 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4242. Min Range: -6.4242
Max Act: 6.2992. Min Act: -0.1700
Data Index: 7868542 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4242. Min Range: -6.4242
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2738054 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4242. Min Range: -6.4242
Max Act: 6.0179. Min Act: -0.1700
Data Index: 942571 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.9554. Min Act: -0.1700
Data Index: 4546392 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.9242. Min Act: -0.1700
Data Index: 2326135 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.9554. Min Act: -0.1700
Data Index: 1141235 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8929. Min Act: -0.1700
Data Index: 143913 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.9242. Min Act: -0.1700
Data Index: 4344837 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8929. Min Act: -0.1700
Data Index: 1400479 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8929. Min Act: -0.1700
Data Index: 7273264 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8929. Min Act: -0.1700
Data Index: 438928 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8304. Min Act: -0.1700
Data Index: 6454156 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.9242. Min Act: -0.1700
Data Index: 2718203 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8929. Min Act: -0.1700
Data Index: 2095403 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8617. Min Act: -0.1700
Data Index: 4180050 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8617. Min Act: -0.1700
Data Index: 6112229 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.7679. Min Act: -0.1700
Data Index: 7269773 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.8304. Min Act: -0.1700
Data Index: 8378126 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4242. Min Range: -6.4242
Max Act: 5.7992. Min Act: -0.1700
Data Index: 7808573 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19