Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2087. Min Range: -9.2087
Max Act: 9.2087. Min Act: -0.1700
Data Index: 3135543 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.4587. Min Act: -0.1700
Data Index: 5633307 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.3962. Min Act: -0.1700
Data Index: 5917882 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.2712. Min Act: -0.1700
Data Index: 6649967 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.0837. Min Act: -0.1700
Data Index: 548830 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.0837. Min Act: -0.1700
Data Index: 6331851 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.0212. Min Act: -0.1700
Data Index: 1052048 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.0837. Min Act: -0.1700
Data Index: 2704519 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 8805985 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 8301720 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2087. Min Range: -9.2087
Max Act: 8.0212. Min Act: -0.1700
Data Index: 5254204 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 6614730 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.9587. Min Act: -0.1700
Data Index: 745595 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 5941177 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.8962. Min Act: -0.1700
Data Index: 3168351 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 6265550 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.8962. Min Act: -0.1700
Data Index: 8382181 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 3487823 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.7712. Min Act: -0.1700
Data Index: 553638 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2087. Min Range: -9.2087
Max Act: 7.8337. Min Act: -0.1700
Data Index: 5644212 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19