Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.5302. Min Act: -0.1700
Data Index: 6375665 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.5302. Min Act: -0.1700
Data Index: 570038 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.5302. Min Act: -0.1700
Data Index: 2140845 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.5302. Min Act: -0.1700
Data Index: 5912399 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.4677. Min Act: -0.1700
Data Index: 521836 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.4052. Min Act: -0.1700
Data Index: 5263463 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.3740. Min Act: -0.1700
Data Index: 6554559 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.4052. Min Act: -0.1700
Data Index: 8255165 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.3427. Min Act: -0.1700
Data Index: 7316467 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.3740. Min Act: -0.1700
Data Index: 7026089 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.3115. Min Act: -0.1700
Data Index: 7541096 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2802. Min Act: -0.1700
Data Index: 8800864 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2490. Min Act: -0.1700
Data Index: 5000216 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2802. Min Act: -0.1700
Data Index: 4715048 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2802. Min Act: -0.1700
Data Index: 8542137 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2490. Min Act: -0.1700
Data Index: 5145935 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2490. Min Act: -0.1700
Data Index: 8598674 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2177. Min Act: -0.1700
Data Index: 2445771 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.1865. Min Act: -0.1700
Data Index: 7298113 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5302. Min Range: -7.5302
Max Act: 7.2177. Min Act: -0.1700
Data Index: 6181411 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19