Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.5873. Min Act: -0.1700
Data Index: 4459457 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.4623. Min Act: -0.1700
Data Index: 130431 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.3998. Min Act: -0.1700
Data Index: 6737143 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.3998. Min Act: -0.1700
Data Index: 1247220 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.2123. Min Act: -0.1700
Data Index: 1796879 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.1498. Min Act: -0.1700
Data Index: 296130 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.1498. Min Act: -0.1700
Data Index: 795556 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.0873. Min Act: -0.1700
Data Index: 5351364 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.0873. Min Act: -0.1700
Data Index: 2304404 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.9623. Min Act: -0.1700
Data Index: 4942084 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5873. Min Range: -12.5873
Max Act: 12.0248. Min Act: -0.1700
Data Index: 5151926 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.9623. Min Act: -0.1700
Data Index: 3007041 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8998. Min Act: -0.1700
Data Index: 2301454 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8998. Min Act: -0.1700
Data Index: 2421269 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8373. Min Act: -0.1700
Data Index: 1015210 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8373. Min Act: -0.1700
Data Index: 7538092 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8373. Min Act: -0.1700
Data Index: 185673 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8373. Min Act: -0.1700
Data Index: 2587423 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.7748. Min Act: -0.1700
Data Index: 5240415 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5873. Min Range: -12.5873
Max Act: 11.8373. Min Act: -0.1700
Data Index: 4572085 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19