Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.8822. Min Act: -0.1700
Data Index: 3455748 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.6322. Min Act: -0.1700
Data Index: 612083 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.4447. Min Act: -0.1700
Data Index: 76633 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.3822. Min Act: -0.1700
Data Index: 2516164 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.2885. Min Act: -0.1700
Data Index: 1560077 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.2572. Min Act: -0.1700
Data Index: 8183305 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.2572. Min Act: -0.1700
Data Index: 8627025 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.2260. Min Act: -0.1700
Data Index: 5388429 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.2260. Min Act: -0.1700
Data Index: 2582098 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.1947. Min Act: -0.1700
Data Index: 708389 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.1635. Min Act: -0.1700
Data Index: 3908192 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.1635. Min Act: -0.1700
Data Index: 3811463 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.1322. Min Act: -0.1700
Data Index: 706243 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.1322. Min Act: -0.1700
Data Index: 4902940 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.1010. Min Act: -0.1700
Data Index: 7425300 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.0697. Min Act: -0.1700
Data Index: 3892527 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.0697. Min Act: -0.1700
Data Index: 7543946 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.0385. Min Act: -0.1700
Data Index: 8363889 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.0385. Min Act: -0.1700
Data Index: 985375 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8822. Min Range: -5.8822
Max Act: 5.0072. Min Act: -0.1700
Data Index: 53808 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19