Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.6735. Min Act: -0.1700
Data Index: 2180105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.6093. Min Act: -0.1700
Data Index: 1443545 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.5932. Min Act: -0.1700
Data Index: 945814 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.5610. Min Act: -0.1700
Data Index: 3124374 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.5287. Min Act: -0.1700
Data Index: 5755974 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.5287. Min Act: -0.1700
Data Index: 7799309 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.5287. Min Act: -0.1700
Data Index: 3142622 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.5125. Min Act: -0.1700
Data Index: 8591448 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 4131271 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4963. Min Act: -0.1700
Data Index: 4092684 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 2281907 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 1490315 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 884202 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 2019847 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4963. Min Act: -0.1700
Data Index: 557034 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 2587925 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 3625081 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 3171956 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4639. Min Act: -0.1700
Data Index: 1247677 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6735. Min Range: -2.6735
Max Act: 2.4801. Min Act: -0.1700
Data Index: 3154825 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19