Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.6835. Min Act: -0.1700
Data Index: 3526448 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.6210. Min Act: -0.1700
Data Index: 6406388 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5585. Min Act: -0.1700
Data Index: 3309684 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4647. Min Act: -0.1700
Data Index: 2566935 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4960. Min Act: -0.1700
Data Index: 3526447 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4335. Min Act: -0.1700
Data Index: 4790194 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4022. Min Act: -0.1700
Data Index: 4640677 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.3397. Min Act: -0.1700
Data Index: 6366714 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.3397. Min Act: -0.1700
Data Index: 4860609 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.3397. Min Act: -0.1700
Data Index: 7553866 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.3085. Min Act: -0.1700
Data Index: 4323352 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.3397. Min Act: -0.1700
Data Index: 5671409 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2772. Min Act: -0.1700
Data Index: 7253584 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2772. Min Act: -0.1700
Data Index: 8454155 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2460. Min Act: -0.1700
Data Index: 5850811 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2460. Min Act: -0.1700
Data Index: 7595602 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2460. Min Act: -0.1700
Data Index: 6797387 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2460. Min Act: -0.1700
Data Index: 4042859 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2460. Min Act: -0.1700
Data Index: 6027632 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.2147. Min Act: -0.1700
Data Index: 7520859 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19