Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2740. Min Act: -0.1700
Data Index: 8190575 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2427. Min Act: -0.1700
Data Index: 6962935 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2115. Min Act: -0.1700
Data Index: 8578541 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2115. Min Act: -0.1700
Data Index: 842684 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.2115. Min Act: -0.1700
Data Index: 6795266 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1802. Min Act: -0.1700
Data Index: 8661899 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1490. Min Act: -0.1700
Data Index: 4665821 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1177. Min Act: -0.1700
Data Index: 8176703 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1490. Min Act: -0.1700
Data Index: 2785219 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1177. Min Act: -0.1700
Data Index: 1602374 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0865. Min Act: -0.1700
Data Index: 5539891 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.1177. Min Act: -0.1700
Data Index: 6365292 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0240. Min Act: -0.1700
Data Index: 8163773 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0552. Min Act: -0.1700
Data Index: 7481 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0240. Min Act: -0.1700
Data Index: 3475107 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 7368257 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2740. Min Range: -6.2740
Max Act: 6.0240. Min Act: -0.1700
Data Index: 889793 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 1402580 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 4225690 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2740. Min Range: -6.2740
Max Act: 5.9927. Min Act: -0.1700
Data Index: 1610644 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19