Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2348 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0429. Min Range: -6.0429
Max Act: 6.0429. Min Act: -0.1700
Data Index: 7298194 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.9179. Min Act: -0.1700
Data Index: 2584089 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.8866. Min Act: -0.1700
Data Index: 3113991 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.7929. Min Act: -0.1700
Data Index: 4701800 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6991. Min Act: -0.1700
Data Index: 6244264 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6679. Min Act: -0.1700
Data Index: 4813622 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6679. Min Act: -0.1700
Data Index: 4298913 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6366. Min Act: -0.1700
Data Index: 6582793 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6366. Min Act: -0.1700
Data Index: 207838 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6366. Min Act: -0.1700
Data Index: 7456404 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6679. Min Act: -0.1700
Data Index: 6593912 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6054. Min Act: -0.1700
Data Index: 6789795 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3868984 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5741. Min Act: -0.1700
Data Index: 6628974 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5741. Min Act: -0.1700
Data Index: 3052470 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5741. Min Act: -0.1700
Data Index: 7410847 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5429. Min Act: -0.1700
Data Index: 4677142 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5429. Min Act: -0.1700
Data Index: 71372 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5429. Min Act: -0.1700
Data Index: 79861 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0429. Min Range: -6.0429
Max Act: 5.5116. Min Act: -0.1700
Data Index: 615888 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19