Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.2239. Min Act: -0.1700
Data Index: 4499802 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0979. Min Act: -0.1700
Data Index: 4866505 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0979. Min Act: -0.1700
Data Index: 11062 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0664. Min Act: -0.1700
Data Index: 4239021 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0664. Min Act: -0.1700
Data Index: 2700758 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0348. Min Act: -0.1700
Data Index: 7951499 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0506. Min Act: -0.1700
Data Index: 6803318 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0348. Min Act: -0.1700
Data Index: 1559464 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0664. Min Act: -0.1700
Data Index: 7309725 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0348. Min Act: -0.1700
Data Index: 1313201 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0348. Min Act: -0.1700
Data Index: 7957733 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0506. Min Act: -0.1700
Data Index: 6279627 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0191. Min Act: -0.1700
Data Index: 1247317 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0033. Min Act: -0.1700
Data Index: 5367667 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0033. Min Act: -0.1700
Data Index: 8188596 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0033. Min Act: -0.1700
Data Index: 2104022 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0191. Min Act: -0.1700
Data Index: 7113133 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0033. Min Act: -0.1700
Data Index: 5956493 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2239. Min Range: -3.2239
Max Act: 3.0033. Min Act: -0.1700
Data Index: 2613086 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2239. Min Range: -3.2239
Max Act: 2.9716. Min Act: -0.1700
Data Index: 5518832 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19