Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4804 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2817. Min Range: -9.2817
Max Act: 9.2817. Min Act: -0.1700
Data Index: 6571034 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.7817. Min Act: -0.1700
Data Index: 2113256 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.7817. Min Act: -0.1700
Data Index: 2449238 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.6567. Min Act: -0.1700
Data Index: 3073332 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5942. Min Act: -0.1700
Data Index: 67811 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5317. Min Act: -0.1700
Data Index: 1422762 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5317. Min Act: -0.1700
Data Index: 208262 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5317. Min Act: -0.1700
Data Index: 5144621 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5317. Min Act: -0.1700
Data Index: 6188604 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5942. Min Act: -0.1700
Data Index: 5426918 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.5317. Min Act: -0.1700
Data Index: 5653435 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4692. Min Act: -0.1700
Data Index: 162318 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4692. Min Act: -0.1700
Data Index: 4456023 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4692. Min Act: -0.1700
Data Index: 291023 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4692. Min Act: -0.1700
Data Index: 8287901 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4692. Min Act: -0.1700
Data Index: 7092666 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4692. Min Act: -0.1700
Data Index: 4256834 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4067. Min Act: -0.1700
Data Index: 5974778 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.3442. Min Act: -0.1700
Data Index: 439414 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2817. Min Range: -9.2817
Max Act: 8.4067. Min Act: -0.1700
Data Index: 234865 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19