Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3132 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8952. Min Act: -0.1700
Data Index: 8505875 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8639. Min Act: -0.1700
Data Index: 8137188 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8014. Min Act: -0.1700
Data Index: 2598480 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8014. Min Act: -0.1700
Data Index: 5644833 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8014. Min Act: -0.1700
Data Index: 1005264 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8014. Min Act: -0.1700
Data Index: 8693154 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8014. Min Act: -0.1700
Data Index: 8688713 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4378043 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7702. Min Act: -0.1700
Data Index: 5237812 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7389. Min Act: -0.1700
Data Index: 6916666 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6152429 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 5370635 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 2228710 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 3239579 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 7578143 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 8137187 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6139. Min Act: -0.1700
Data Index: 4156385 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 308324 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5827. Min Act: -0.1700
Data Index: 7202858 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5827. Min Act: -0.1700
Data Index: 8414293 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19