Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2343 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.4585. Min Act: -0.1700
Data Index: 4103211 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.4742. Min Act: -0.1700
Data Index: 21450 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.4272. Min Act: -0.1700
Data Index: 8506651 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.4115. Min Act: -0.1700
Data Index: 4999584 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3958. Min Act: -0.1700
Data Index: 6261029 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3645. Min Act: -0.1700
Data Index: 7833607 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3958. Min Act: -0.1700
Data Index: 194636 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3645. Min Act: -0.1700
Data Index: 34155 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3331. Min Act: -0.1700
Data Index: 2057462 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3017. Min Act: -0.1700
Data Index: 4465394 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2860. Min Act: -0.1700
Data Index: 8479329 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.3017. Min Act: -0.1700
Data Index: 7998752 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2389. Min Act: -0.1700
Data Index: 437053 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2860. Min Act: -0.1700
Data Index: 4608248 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2703. Min Act: -0.1700
Data Index: 7395674 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2546. Min Act: -0.1700
Data Index: 1300783 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2703. Min Act: -0.1700
Data Index: 1899426 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2546. Min Act: -0.1700
Data Index: 3202949 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2232. Min Act: -0.1700
Data Index: 869525 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4742. Min Range: -3.4742
Max Act: 3.2232. Min Act: -0.1700
Data Index: 6397369 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19