Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5487 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.4489. Min Act: -0.1700
Data Index: 4259614 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.4489. Min Act: -0.1700
Data Index: 1868403 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.3864. Min Act: -0.1700
Data Index: 7816541 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.3864. Min Act: -0.1700
Data Index: 4401598 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.3239. Min Act: -0.1700
Data Index: 2124591 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 3301633 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 1346445 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 8578560 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.0114. Min Act: -0.1700
Data Index: 8038511 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.0114. Min Act: -0.1700
Data Index: 7283681 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4489. Min Range: -9.4489
Max Act: 9.0114. Min Act: -0.1700
Data Index: 7559565 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8864. Min Act: -0.1700
Data Index: 5626896 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8864. Min Act: -0.1700
Data Index: 2185629 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8864. Min Act: -0.1700
Data Index: 2330479 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8864. Min Act: -0.1700
Data Index: 4304657 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8864. Min Act: -0.1700
Data Index: 4120163 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8239. Min Act: -0.1700
Data Index: 4571524 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8239. Min Act: -0.1700
Data Index: 6218960 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8239. Min Act: -0.1700
Data Index: 4933430 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4489. Min Range: -9.4489
Max Act: 8.8239. Min Act: -0.1700
Data Index: 5132872 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19