Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3769 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.6463. Min Act: -0.1700
Data Index: 8497529 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2859. Min Act: -0.1700
Data Index: 2893393 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2545. Min Act: -0.1700
Data Index: 7689793 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2702. Min Act: -0.1700
Data Index: 5988442 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2545. Min Act: -0.1700
Data Index: 2498390 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2073. Min Act: -0.1700
Data Index: 1717244 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1916. Min Act: -0.1700
Data Index: 2640819 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1759. Min Act: -0.1700
Data Index: 3730683 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1444. Min Act: -0.1700
Data Index: 4073453 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1916. Min Act: -0.1700
Data Index: 7832374 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1916. Min Act: -0.1700
Data Index: 178198 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1601. Min Act: -0.1700
Data Index: 625231 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1601. Min Act: -0.1700
Data Index: 2021396 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1601. Min Act: -0.1700
Data Index: 2497818 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1601. Min Act: -0.1700
Data Index: 912453 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1286. Min Act: -0.1700
Data Index: 8638070 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1286. Min Act: -0.1700
Data Index: 233466 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1444. Min Act: -0.1700
Data Index: 8595606 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1286. Min Act: -0.1700
Data Index: 7792572 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1286. Min Act: -0.1700
Data Index: 7240281 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19