Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5794 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6893. Min Range: -10.6893
Max Act: 10.6893. Min Act: -0.1700
Data Index: 5194410 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6893. Min Range: -10.6893
Max Act: 10.4393. Min Act: -0.1700
Data Index: 973727 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6893. Min Range: -10.6893
Max Act: 10.2518. Min Act: -0.1700
Data Index: 8290011 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6893. Min Range: -10.6893
Max Act: 10.2518. Min Act: -0.1700
Data Index: 3865765 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6893. Min Range: -10.6893
Max Act: 10.0643. Min Act: -0.1700
Data Index: 8007412 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.8768. Min Act: -0.1700
Data Index: 3501053 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.7518. Min Act: -0.1700
Data Index: 1329352 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.7518. Min Act: -0.1700
Data Index: 1578131 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.7518. Min Act: -0.1700
Data Index: 4147448 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.6893. Min Act: -0.1700
Data Index: 3825412 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.6893. Min Act: -0.1700
Data Index: 8570984 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.6268. Min Act: -0.1700
Data Index: 678090 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.6268. Min Act: -0.1700
Data Index: 3179053 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.6268. Min Act: -0.1700
Data Index: 6784532 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.5643. Min Act: -0.1700
Data Index: 5664969 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.5643. Min Act: -0.1700
Data Index: 8328428 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.5643. Min Act: -0.1700
Data Index: 5837124 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.5643. Min Act: -0.1700
Data Index: 4826305 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.5018. Min Act: -0.1700
Data Index: 1966422 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6893. Min Range: -10.6893
Max Act: 9.4393. Min Act: -0.1700
Data Index: 4197534 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19