Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.5480. Min Act: -0.1700
Data Index: 873990 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.4855. Min Act: -0.1700
Data Index: 7809773 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.4855. Min Act: -0.1700
Data Index: 5852269 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.4230. Min Act: -0.1700
Data Index: 1933361 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2980. Min Act: -0.1700
Data Index: 4314240 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2980. Min Act: -0.1700
Data Index: 3301067 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2980. Min Act: -0.1700
Data Index: 4367367 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2980. Min Act: -0.1700
Data Index: 3096500 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2980. Min Act: -0.1700
Data Index: 1624802 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2355. Min Act: -0.1700
Data Index: 7886023 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2355. Min Act: -0.1700
Data Index: 4682916 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2355. Min Act: -0.1700
Data Index: 7555882 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.2355. Min Act: -0.1700
Data Index: 7302511 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.1730. Min Act: -0.1700
Data Index: 1779640 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.1730. Min Act: -0.1700
Data Index: 2019494 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.1105. Min Act: -0.1700
Data Index: 5186495 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.1105. Min Act: -0.1700
Data Index: 2244119 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.0480. Min Act: -0.1700
Data Index: 2929071 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.1730. Min Act: -0.1700
Data Index: 2376510 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5480. Min Range: -9.5480
Max Act: 9.1105. Min Act: -0.1700
Data Index: 639923 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19