Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.8632. Min Act: -0.1700
Data Index: 8766013 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.8319. Min Act: -0.1700
Data Index: 5979407 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.6132. Min Act: -0.1700
Data Index: 417964 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.6132. Min Act: -0.1700
Data Index: 8068786 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.5507. Min Act: -0.1700
Data Index: 2414033 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.4257. Min Act: -0.1700
Data Index: 5395737 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.3632. Min Act: -0.1700
Data Index: 485351 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.3319. Min Act: -0.1700
Data Index: 802738 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.3319. Min Act: -0.1700
Data Index: 4037314 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2694. Min Act: -0.1700
Data Index: 348580 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2694. Min Act: -0.1700
Data Index: 5580758 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 3886679 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2694. Min Act: -0.1700
Data Index: 5544211 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2069. Min Act: -0.1700
Data Index: 2519590 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 3852408 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2382. Min Act: -0.1700
Data Index: 1878893 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2069. Min Act: -0.1700
Data Index: 4827599 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2069. Min Act: -0.1700
Data Index: 4735917 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.2069. Min Act: -0.1700
Data Index: 274179 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8632. Min Range: -5.8632
Max Act: 5.1132. Min Act: -0.1700
Data Index: 2453251 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19