Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.7194. Min Act: -0.1700
Data Index: 2890780 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.6569. Min Act: -0.1700
Data Index: 2115809 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.6257. Min Act: -0.1700
Data Index: 700962 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.5319. Min Act: -0.1700
Data Index: 6552804 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.5007. Min Act: -0.1700
Data Index: 7296110 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.4382. Min Act: -0.1700
Data Index: 8805713 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3757. Min Act: -0.1700
Data Index: 3575823 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3444. Min Act: -0.1700
Data Index: 8440901 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3444. Min Act: -0.1700
Data Index: 8537680 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3444. Min Act: -0.1700
Data Index: 4390232 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3132. Min Act: -0.1700
Data Index: 7799212 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3132. Min Act: -0.1700
Data Index: 1113947 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.3132. Min Act: -0.1700
Data Index: 6153754 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2819. Min Act: -0.1700
Data Index: 2229190 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2819. Min Act: -0.1700
Data Index: 6102016 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2507. Min Act: -0.1700
Data Index: 7209463 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2507. Min Act: -0.1700
Data Index: 4385962 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2819. Min Act: -0.1700
Data Index: 6598301 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2507. Min Act: -0.1700
Data Index: 1113939 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7194. Min Range: -6.7194
Max Act: 6.2194. Min Act: -0.1700
Data Index: 3302950 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19