Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4210 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.4833. Min Act: -0.1700
Data Index: 4041552 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.4833. Min Act: -0.1700
Data Index: 6708708 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.5145. Min Act: -0.1700
Data Index: 1601160 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.4520. Min Act: -0.1700
Data Index: 1509385 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.4520. Min Act: -0.1700
Data Index: 1587911 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.3895. Min Act: -0.1700
Data Index: 5308879 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.3895. Min Act: -0.1700
Data Index: 4684309 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.3270. Min Act: -0.1700
Data Index: 8372871 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.3270. Min Act: -0.1700
Data Index: 8377241 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2645. Min Act: -0.1700
Data Index: 6763291 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2645. Min Act: -0.1700
Data Index: 3897937 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2333. Min Act: -0.1700
Data Index: 3211072 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2333. Min Act: -0.1700
Data Index: 2143731 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2020. Min Act: -0.1700
Data Index: 6283573 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3464780 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1708. Min Act: -0.1700
Data Index: 6048988 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1708. Min Act: -0.1700
Data Index: 5799327 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1708. Min Act: -0.1700
Data Index: 2606642 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1395. Min Act: -0.1700
Data Index: 2540546 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1395. Min Act: -0.1700
Data Index: 4313266 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19