Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.6866. Min Act: -0.1700
Data Index: 4753576 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.6241. Min Act: -0.1700
Data Index: 2380332 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.5616. Min Act: -0.1700
Data Index: 8374751 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.5303. Min Act: -0.1700
Data Index: 7393907 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.5303. Min Act: -0.1700
Data Index: 5857540 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.4991. Min Act: -0.1700
Data Index: 6489608 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.4991. Min Act: -0.1700
Data Index: 89150 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.4053. Min Act: -0.1700
Data Index: 203687 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3741. Min Act: -0.1700
Data Index: 6821828 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3741. Min Act: -0.1700
Data Index: 4748929 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3428. Min Act: -0.1700
Data Index: 6931657 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3428. Min Act: -0.1700
Data Index: 6986895 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3116. Min Act: -0.1700
Data Index: 4012005 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3116. Min Act: -0.1700
Data Index: 1819335 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.2803. Min Act: -0.1700
Data Index: 7906451 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.2803. Min Act: -0.1700
Data Index: 3591432 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.3116. Min Act: -0.1700
Data Index: 924478 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.2803. Min Act: -0.1700
Data Index: 8461317 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.2178. Min Act: -0.1700
Data Index: 2946983 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6866. Min Range: -6.6866
Max Act: 6.2491. Min Act: -0.1700
Data Index: 3553573 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19