Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0557. Min Range: -4.0557
Max Act: 4.0557. Min Act: -0.1700
Data Index: 7426819 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8994. Min Act: -0.1700
Data Index: 7979374 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.9306. Min Act: -0.1700
Data Index: 4030747 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8994. Min Act: -0.1700
Data Index: 8555016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8994. Min Act: -0.1700
Data Index: 2055415 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8994. Min Act: -0.1700
Data Index: 7989959 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8994. Min Act: -0.1700
Data Index: 476393 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8681. Min Act: -0.1700
Data Index: 3241573 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8368. Min Act: -0.1700
Data Index: 5812272 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8368. Min Act: -0.1700
Data Index: 1646675 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8681. Min Act: -0.1700
Data Index: 4174532 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8994. Min Act: -0.1700
Data Index: 4884766 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8681. Min Act: -0.1700
Data Index: 7437875 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8681. Min Act: -0.1700
Data Index: 2828248 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8368. Min Act: -0.1700
Data Index: 1672896 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8368. Min Act: -0.1700
Data Index: 606453 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8681. Min Act: -0.1700
Data Index: 2361328 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8056. Min Act: -0.1700
Data Index: 3362623 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8368. Min Act: -0.1700
Data Index: 566402 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0557. Min Range: -4.0557
Max Act: 3.8056. Min Act: -0.1700
Data Index: 4341541 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19