Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1439 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0532. Min Act: -0.1700
Data Index: 5537584 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0059. Min Act: -0.1700
Data Index: 5158885 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9901. Min Act: -0.1700
Data Index: 4500083 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9584. Min Act: -0.1700
Data Index: 4500085 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9109. Min Act: -0.1700
Data Index: 7783806 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9268. Min Act: -0.1700
Data Index: 3494299 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9268. Min Act: -0.1700
Data Index: 3494304 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8792. Min Act: -0.1700
Data Index: 4500084 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9109. Min Act: -0.1700
Data Index: 241640 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8792. Min Act: -0.1700
Data Index: 5537580 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8792. Min Act: -0.1700
Data Index: 4726923 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8474. Min Act: -0.1700
Data Index: 1421235 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8315. Min Act: -0.1700
Data Index: 626818 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8474. Min Act: -0.1700
Data Index: 600423 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8156. Min Act: -0.1700
Data Index: 5537578 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8156. Min Act: -0.1700
Data Index: 7731305 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8156. Min Act: -0.1700
Data Index: 6656619 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.7997. Min Act: -0.1700
Data Index: 6221399 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.7997. Min Act: -0.1700
Data Index: 7731304 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.7997. Min Act: -0.1700
Data Index: 6809022 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19