Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.6224. Min Act: -0.1700
Data Index: 2629982 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.5912. Min Act: -0.1700
Data Index: 2033716 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.5599. Min Act: -0.1700
Data Index: 6445142 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.5287. Min Act: -0.1700
Data Index: 930938 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.5287. Min Act: -0.1700
Data Index: 2617098 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2264130 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.4037. Min Act: -0.1700
Data Index: 3121494 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.4037. Min Act: -0.1700
Data Index: 3052032 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.3724. Min Act: -0.1700
Data Index: 605621 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.3099. Min Act: -0.1700
Data Index: 5674721 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.3412. Min Act: -0.1700
Data Index: 3526635 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.3099. Min Act: -0.1700
Data Index: 2901926 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.3099. Min Act: -0.1700
Data Index: 5060356 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.2787. Min Act: -0.1700
Data Index: 5939807 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.3099. Min Act: -0.1700
Data Index: 144720 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.2474. Min Act: -0.1700
Data Index: 6794093 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.2474. Min Act: -0.1700
Data Index: 7608369 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.2474. Min Act: -0.1700
Data Index: 5911006 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.2474. Min Act: -0.1700
Data Index: 1292198 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6224. Min Range: -5.6224
Max Act: 5.2474. Min Act: -0.1700
Data Index: 5153025 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19