Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 191 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.9498. Min Act: -0.1700
Data Index: 8117347 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.8873. Min Act: -0.1700
Data Index: 325038 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.6060. Min Act: -0.1700
Data Index: 931960 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.4185. Min Act: -0.1700
Data Index: 1107025 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.4185. Min Act: -0.1700
Data Index: 8018306 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.2935. Min Act: -0.1700
Data Index: 3496663 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.2310. Min Act: -0.1700
Data Index: 6889970 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.1998. Min Act: -0.1700
Data Index: 1204270 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.1373. Min Act: -0.1700
Data Index: 5348332 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.1060. Min Act: -0.1700
Data Index: 7471913 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.1373. Min Act: -0.1700
Data Index: 7844556 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.1060. Min Act: -0.1700
Data Index: 5069309 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.0435. Min Act: -0.1700
Data Index: 8188543 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.0435. Min Act: -0.1700
Data Index: 4885733 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.0435. Min Act: -0.1700
Data Index: 8667645 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.0435. Min Act: -0.1700
Data Index: 6409819 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9498. Min Range: -7.9498
Max Act: 7.0435. Min Act: -0.1700
Data Index: 3897226 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9498. Min Range: -7.9498
Max Act: 6.9498. Min Act: -0.1700
Data Index: 7986909 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9498. Min Range: -7.9498
Max Act: 6.9498. Min Act: -0.1700
Data Index: 932198 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9498. Min Range: -7.9498
Max Act: 6.9810. Min Act: -0.1700
Data Index: 785079 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19