Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1286 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.5064. Min Act: -0.1700
Data Index: 7051286 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.1626. Min Act: -0.1700
Data Index: 2591744 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.1314. Min Act: -0.1700
Data Index: 1089154 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.1001. Min Act: -0.1700
Data Index: 4220363 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.0376. Min Act: -0.1700
Data Index: 7914415 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4004343 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.0064. Min Act: -0.1700
Data Index: 8767690 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.0064. Min Act: -0.1700
Data Index: 2587455 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.0064. Min Act: -0.1700
Data Index: 3933993 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5064. Min Range: -7.5064
Max Act: 7.0064. Min Act: -0.1700
Data Index: 6283728 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9439. Min Act: -0.1700
Data Index: 3653338 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9751. Min Act: -0.1700
Data Index: 4705444 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9439. Min Act: -0.1700
Data Index: 3033279 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9439. Min Act: -0.1700
Data Index: 1472755 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9126. Min Act: -0.1700
Data Index: 8756309 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9126. Min Act: -0.1700
Data Index: 763271 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.9126. Min Act: -0.1700
Data Index: 7156895 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.8814. Min Act: -0.1700
Data Index: 2514969 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.8814. Min Act: -0.1700
Data Index: 5527300 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5064. Min Range: -7.5064
Max Act: 6.8814. Min Act: -0.1700
Data Index: 1400841 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19