Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.6110. Min Act: -0.1700
Data Index: 7778230 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.6110. Min Act: -0.1700
Data Index: 4397287 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.5173. Min Act: -0.1700
Data Index: 6650900 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.4548. Min Act: -0.1700
Data Index: 4498281 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.4548. Min Act: -0.1700
Data Index: 6827562 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.3610. Min Act: -0.1700
Data Index: 1797341 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.3297. Min Act: -0.1700
Data Index: 8537359 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.3297. Min Act: -0.1700
Data Index: 171569 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2985. Min Act: -0.1700
Data Index: 7898849 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2985. Min Act: -0.1700
Data Index: 4401163 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2985. Min Act: -0.1700
Data Index: 194014 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2985. Min Act: -0.1700
Data Index: 6535169 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2985. Min Act: -0.1700
Data Index: 6125030 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2985. Min Act: -0.1700
Data Index: 4894036 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2360. Min Act: -0.1700
Data Index: 7012588 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2360. Min Act: -0.1700
Data Index: 5085467 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2360. Min Act: -0.1700
Data Index: 3627939 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2360. Min Act: -0.1700
Data Index: 231075 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2047. Min Act: -0.1700
Data Index: 6706969 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6110. Min Range: -4.6110
Max Act: 4.2047. Min Act: -0.1700
Data Index: 887534 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19