Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4096228 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2350146 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.1217. Min Act: -0.1700
Data Index: 4505002 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.1529. Min Act: -0.1700
Data Index: 6125556 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.1529. Min Act: -0.1700
Data Index: 6828465 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0904. Min Act: -0.1700
Data Index: 7566068 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0592. Min Act: -0.1700
Data Index: 7132047 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0592. Min Act: -0.1700
Data Index: 5040187 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.1217. Min Act: -0.1700
Data Index: 5237237 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0592. Min Act: -0.1700
Data Index: 3509788 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0904. Min Act: -0.1700
Data Index: 1457172 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0904. Min Act: -0.1700
Data Index: 524450 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0279. Min Act: -0.1700
Data Index: 1832358 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0592. Min Act: -0.1700
Data Index: 8132224 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0279. Min Act: -0.1700
Data Index: 6969739 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0279. Min Act: -0.1700
Data Index: 7046873 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2467. Min Range: -4.2467
Max Act: 3.9967. Min Act: -0.1700
Data Index: 7305775 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2467. Min Range: -4.2467
Max Act: 3.9967. Min Act: -0.1700
Data Index: 6665755 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2467. Min Range: -4.2467
Max Act: 4.0592. Min Act: -0.1700
Data Index: 489469 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2467. Min Range: -4.2467
Max Act: 3.9967. Min Act: -0.1700
Data Index: 7237617 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19