Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4197 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0035. Min Range: -4.0035
Max Act: 4.0035. Min Act: -0.1700
Data Index: 1834266 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.9410. Min Act: -0.1700
Data Index: 4745290 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.9097. Min Act: -0.1700
Data Index: 4550969 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.8159. Min Act: -0.1700
Data Index: 5437721 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.8159. Min Act: -0.1700
Data Index: 8499053 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.8159. Min Act: -0.1700
Data Index: 2661918 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7847. Min Act: -0.1700
Data Index: 2743583 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7534. Min Act: -0.1700
Data Index: 6700657 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7534. Min Act: -0.1700
Data Index: 2277293 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7534. Min Act: -0.1700
Data Index: 2232627 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7534. Min Act: -0.1700
Data Index: 6295744 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7847. Min Act: -0.1700
Data Index: 5484810 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7221. Min Act: -0.1700
Data Index: 2446372 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.6908. Min Act: -0.1700
Data Index: 7859037 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7221. Min Act: -0.1700
Data Index: 3908539 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7221. Min Act: -0.1700
Data Index: 4115184 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7221. Min Act: -0.1700
Data Index: 3345215 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7534. Min Act: -0.1700
Data Index: 8104218 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7221. Min Act: -0.1700
Data Index: 774797 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0035. Min Range: -4.0035
Max Act: 3.7221. Min Act: -0.1700
Data Index: 1897267 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19