Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4939 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.9325. Min Act: -0.1700
Data Index: 8365382 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.8075. Min Act: -0.1700
Data Index: 3915406 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.8075. Min Act: -0.1700
Data Index: 5865590 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.8075. Min Act: -0.1700
Data Index: 8204374 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.7450. Min Act: -0.1700
Data Index: 8157899 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.6825. Min Act: -0.1700
Data Index: 6672615 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.6825. Min Act: -0.1700
Data Index: 5959068 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.6825. Min Act: -0.1700
Data Index: 429404 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.6200. Min Act: -0.1700
Data Index: 1302982 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5575. Min Act: -0.1700
Data Index: 1323299 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.6200. Min Act: -0.1700
Data Index: 2277681 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.6200. Min Act: -0.1700
Data Index: 938810 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5575. Min Act: -0.1700
Data Index: 7673450 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5575. Min Act: -0.1700
Data Index: 3873746 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5575. Min Act: -0.1700
Data Index: 4334329 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5263. Min Act: -0.1700
Data Index: 7301983 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5263. Min Act: -0.1700
Data Index: 3002941 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5263. Min Act: -0.1700
Data Index: 5983031 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.5263. Min Act: -0.1700
Data Index: 6748337 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9325. Min Range: -7.9325
Max Act: 7.4950. Min Act: -0.1700
Data Index: 1335278 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19