Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1722. Min Range: -6.1722
Max Act: 6.1722. Min Act: -0.1700
Data Index: 3163235 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1722. Min Range: -6.1722
Max Act: 6.0472. Min Act: -0.1700
Data Index: 2790697 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1722. Min Range: -6.1722
Max Act: 6.0159. Min Act: -0.1700
Data Index: 7909876 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1722. Min Range: -6.1722
Max Act: 6.0472. Min Act: -0.1700
Data Index: 7053832 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.9847. Min Act: -0.1700
Data Index: 4729841 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.9222. Min Act: -0.1700
Data Index: 5185947 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.9222. Min Act: -0.1700
Data Index: 2834741 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3036061 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8597. Min Act: -0.1700
Data Index: 1195655 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2175425 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8284. Min Act: -0.1700
Data Index: 8032895 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8284. Min Act: -0.1700
Data Index: 5949001 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8284. Min Act: -0.1700
Data Index: 961794 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8284. Min Act: -0.1700
Data Index: 4417394 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.8284. Min Act: -0.1700
Data Index: 876368 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6515510 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6954514 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.7659. Min Act: -0.1700
Data Index: 1919630 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.7659. Min Act: -0.1700
Data Index: 2496255 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1722. Min Range: -6.1722
Max Act: 5.7659. Min Act: -0.1700
Data Index: 7970511 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19