Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3484. Min Range: -8.3484
Max Act: 8.3484. Min Act: -0.1700
Data Index: 4626053 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3484. Min Range: -8.3484
Max Act: 8.2234. Min Act: -0.1700
Data Index: 5665587 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.7234. Min Act: -0.1700
Data Index: 4821552 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.6921. Min Act: -0.1700
Data Index: 5821598 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.6609. Min Act: -0.1700
Data Index: 4485305 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.5984. Min Act: -0.1700
Data Index: 7965183 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.5671. Min Act: -0.1700
Data Index: 668512 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.5671. Min Act: -0.1700
Data Index: 5482548 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.5359. Min Act: -0.1700
Data Index: 1186128 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.5359. Min Act: -0.1700
Data Index: 4485304 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.4734. Min Act: -0.1700
Data Index: 4124456 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.4421. Min Act: -0.1700
Data Index: 8422837 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.4421. Min Act: -0.1700
Data Index: 427226 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.4109. Min Act: -0.1700
Data Index: 8047849 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.2859. Min Act: -0.1700
Data Index: 5494074 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.3171. Min Act: -0.1700
Data Index: 40285 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.2859. Min Act: -0.1700
Data Index: 5984858 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.3171. Min Act: -0.1700
Data Index: 200827 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.3171. Min Act: -0.1700
Data Index: 1100277 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3484. Min Range: -8.3484
Max Act: 7.3171. Min Act: -0.1700
Data Index: 4109942 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19