Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 119 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.7276. Min Act: -0.1700
Data Index: 2072423 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.4776. Min Act: -0.1700
Data Index: 2983553 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.4776. Min Act: -0.1700
Data Index: 2374931 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.4776. Min Act: -0.1700
Data Index: 7955730 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.4151. Min Act: -0.1700
Data Index: 8466334 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.4151. Min Act: -0.1700
Data Index: 7728659 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.4776. Min Act: -0.1700
Data Index: 4426001 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.3526. Min Act: -0.1700
Data Index: 6835460 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2276. Min Act: -0.1700
Data Index: 3528825 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2901. Min Act: -0.1700
Data Index: 3134648 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2276. Min Act: -0.1700
Data Index: 8033540 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2276. Min Act: -0.1700
Data Index: 6704892 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2901. Min Act: -0.1700
Data Index: 3884637 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2276. Min Act: -0.1700
Data Index: 8513960 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.2901. Min Act: -0.1700
Data Index: 553945 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.1651. Min Act: -0.1700
Data Index: 7428316 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.1651. Min Act: -0.1700
Data Index: 2639331 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.1651. Min Act: -0.1700
Data Index: 2818679 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.0401. Min Act: -0.1700
Data Index: 4918569 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7276. Min Range: -9.7276
Max Act: 9.1026. Min Act: -0.1700
Data Index: 5322738 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19