Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.8254. Min Act: -0.1700
Data Index: 6310507 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.6691. Min Act: -0.1700
Data Index: 5374724 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.6379. Min Act: -0.1700
Data Index: 3414134 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.5754. Min Act: -0.1700
Data Index: 2176551 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.5754. Min Act: -0.1700
Data Index: 8324030 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.5129. Min Act: -0.1700
Data Index: 6716058 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.5129. Min Act: -0.1700
Data Index: 5374721 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4816. Min Act: -0.1700
Data Index: 8693690 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4816. Min Act: -0.1700
Data Index: 6260811 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4191. Min Act: -0.1700
Data Index: 2335030 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4191. Min Act: -0.1700
Data Index: 5817957 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3879. Min Act: -0.1700
Data Index: 2617792 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.4191. Min Act: -0.1700
Data Index: 273519 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3879. Min Act: -0.1700
Data Index: 1123292 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3566. Min Act: -0.1700
Data Index: 566576 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3566. Min Act: -0.1700
Data Index: 1546154 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3254. Min Act: -0.1700
Data Index: 5473954 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3254. Min Act: -0.1700
Data Index: 209021 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.2941. Min Act: -0.1700
Data Index: 3704064 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8254. Min Range: -5.8254
Max Act: 5.3254. Min Act: -0.1700
Data Index: 6892788 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19