Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.7597. Min Act: -0.1700
Data Index: 7527373 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6971. Min Act: -0.1700
Data Index: 3170882 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.6502. Min Act: -0.1700
Data Index: 3173250 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5249. Min Act: -0.1700
Data Index: 5576384 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5249. Min Act: -0.1700
Data Index: 7911869 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5093. Min Act: -0.1700
Data Index: 600764 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4936. Min Act: -0.1700
Data Index: 5865564 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5093. Min Act: -0.1700
Data Index: 1670237 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.5093. Min Act: -0.1700
Data Index: 39682 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4936. Min Act: -0.1700
Data Index: 5765492 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4936. Min Act: -0.1700
Data Index: 6367284 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4780. Min Act: -0.1700
Data Index: 8098130 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4780. Min Act: -0.1700
Data Index: 7113466 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4623. Min Act: -0.1700
Data Index: 6347956 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4466. Min Act: -0.1700
Data Index: 2385618 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4466. Min Act: -0.1700
Data Index: 900419 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4780. Min Act: -0.1700
Data Index: 1141905 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4310. Min Act: -0.1700
Data Index: 4565220 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4466. Min Act: -0.1700
Data Index: 3866567 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7597. Min Range: -3.7597
Max Act: 3.4623. Min Act: -0.1700
Data Index: 2090701 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19