Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.7529. Min Act: -0.1700
Data Index: 5087556 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.5342. Min Act: -0.1700
Data Index: 4690424 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.5029. Min Act: -0.1700
Data Index: 8698767 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.5029. Min Act: -0.1700
Data Index: 6112894 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4717. Min Act: -0.1700
Data Index: 6645716 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4717. Min Act: -0.1700
Data Index: 7401686 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4404. Min Act: -0.1700
Data Index: 546439 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4717. Min Act: -0.1700
Data Index: 8645601 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4092. Min Act: -0.1700
Data Index: 8166319 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4092. Min Act: -0.1700
Data Index: 5583011 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.4092. Min Act: -0.1700
Data Index: 6968798 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3779. Min Act: -0.1700
Data Index: 4471084 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3779. Min Act: -0.1700
Data Index: 1953939 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3779. Min Act: -0.1700
Data Index: 4754879 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3779. Min Act: -0.1700
Data Index: 5121998 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3779. Min Act: -0.1700
Data Index: 3853328 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3779. Min Act: -0.1700
Data Index: 6148153 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3467. Min Act: -0.1700
Data Index: 932724 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3154. Min Act: -0.1700
Data Index: 1050106 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7529. Min Range: -6.7529
Max Act: 6.3467. Min Act: -0.1700
Data Index: 5025166 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19