Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.2043. Min Act: -0.1700
Data Index: 5694340 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.2043. Min Act: -0.1700
Data Index: 1915621 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.1731. Min Act: -0.1700
Data Index: 6381583 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.1418. Min Act: -0.1700
Data Index: 4406566 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.1418. Min Act: -0.1700
Data Index: 638096 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.1418. Min Act: -0.1700
Data Index: 1154612 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.1106. Min Act: -0.1700
Data Index: 6787580 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.0793. Min Act: -0.1700
Data Index: 3840039 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.0480. Min Act: -0.1700
Data Index: 6381587 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.0480. Min Act: -0.1700
Data Index: 6517504 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.0480. Min Act: -0.1700
Data Index: 2733996 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2043. Min Range: -4.2043
Max Act: 4.0168. Min Act: -0.1700
Data Index: 4564297 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9855. Min Act: -0.1700
Data Index: 1165717 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9855. Min Act: -0.1700
Data Index: 7749472 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9855. Min Act: -0.1700
Data Index: 1165716 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9855. Min Act: -0.1700
Data Index: 6716263 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9543. Min Act: -0.1700
Data Index: 6977977 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9543. Min Act: -0.1700
Data Index: 6293628 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9543. Min Act: -0.1700
Data Index: 6527975 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2043. Min Range: -4.2043
Max Act: 3.9230. Min Act: -0.1700
Data Index: 1915628 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19