Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4179. Min Range: -8.4179
Max Act: 8.4179. Min Act: -0.1700
Data Index: 6594963 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4179. Min Range: -8.4179
Max Act: 8.0429. Min Act: -0.1700
Data Index: 3163861 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.9804. Min Act: -0.1700
Data Index: 5088889 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.9804. Min Act: -0.1700
Data Index: 2598300 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.8554. Min Act: -0.1700
Data Index: 6116540 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.8554. Min Act: -0.1700
Data Index: 3299914 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.8241. Min Act: -0.1700
Data Index: 4558068 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.8241. Min Act: -0.1700
Data Index: 4861688 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.6991. Min Act: -0.1700
Data Index: 4916141 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.7304. Min Act: -0.1700
Data Index: 4568075 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.6679. Min Act: -0.1700
Data Index: 4686094 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.6366. Min Act: -0.1700
Data Index: 2452971 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.6366. Min Act: -0.1700
Data Index: 4508523 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5741. Min Act: -0.1700
Data Index: 5270184 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5741. Min Act: -0.1700
Data Index: 1708793 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5741. Min Act: -0.1700
Data Index: 8571407 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5741. Min Act: -0.1700
Data Index: 66279 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5429. Min Act: -0.1700
Data Index: 5673360 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5741. Min Act: -0.1700
Data Index: 3952344 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4179. Min Range: -8.4179
Max Act: 7.5429. Min Act: -0.1700
Data Index: 306292 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19