Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0128. Min Range: -3.0128
Max Act: 3.0128. Min Act: -0.1700
Data Index: 6463755 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.9970. Min Act: -0.1700
Data Index: 6463754 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.9653. Min Act: -0.1700
Data Index: 3253388 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.9653. Min Act: -0.1700
Data Index: 3183772 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.9178. Min Act: -0.1700
Data Index: 5711264 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.9337. Min Act: -0.1700
Data Index: 5209671 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8703. Min Act: -0.1700
Data Index: 312420 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8703. Min Act: -0.1700
Data Index: 7504223 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8385. Min Act: -0.1700
Data Index: 5209672 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8703. Min Act: -0.1700
Data Index: 3765979 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8385. Min Act: -0.1700
Data Index: 7504221 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8385. Min Act: -0.1700
Data Index: 7504222 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8226. Min Act: -0.1700
Data Index: 3967968 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8385. Min Act: -0.1700
Data Index: 7494956 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.8226. Min Act: -0.1700
Data Index: 3539320 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.7907. Min Act: -0.1700
Data Index: 4749516 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.7748. Min Act: -0.1700
Data Index: 8373845 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.7748. Min Act: -0.1700
Data Index: 1913476 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.7748. Min Act: -0.1700
Data Index: 8043279 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0128. Min Range: -3.0128
Max Act: 2.7907. Min Act: -0.1700
Data Index: 4130294 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19