Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.8278. Min Act: -0.1700
Data Index: 3734339 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.8278. Min Act: -0.1700
Data Index: 241013 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.7002. Min Act: -0.1700
Data Index: 6899544 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6682. Min Act: -0.1700
Data Index: 3387926 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6842. Min Act: -0.1700
Data Index: 5112262 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6682. Min Act: -0.1700
Data Index: 3504500 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6682. Min Act: -0.1700
Data Index: 6149634 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6522. Min Act: -0.1700
Data Index: 3797203 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6522. Min Act: -0.1700
Data Index: 7899054 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6682. Min Act: -0.1700
Data Index: 5579803 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6361. Min Act: -0.1700
Data Index: 8199716 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6361. Min Act: -0.1700
Data Index: 8182318 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6200. Min Act: -0.1700
Data Index: 3206978 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6040. Min Act: -0.1700
Data Index: 7437163 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.6040. Min Act: -0.1700
Data Index: 4295622 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.5879. Min Act: -0.1700
Data Index: 1358088 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.5879. Min Act: -0.1700
Data Index: 4519628 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.5717. Min Act: -0.1700
Data Index: 5277558 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.5717. Min Act: -0.1700
Data Index: 6935036 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8278. Min Range: -2.8278
Max Act: 2.5879. Min Act: -0.1700
Data Index: 783485 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19