Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.8643. Min Act: -0.1700
Data Index: 6383980 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.7080. Min Act: -0.1700
Data Index: 1746270 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7666296 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4580. Min Act: -0.1700
Data Index: 5765279 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4268. Min Act: -0.1700
Data Index: 6916607 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 8354278 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 6586572 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 1686518 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 405146 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3330. Min Act: -0.1700
Data Index: 1625613 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3330. Min Act: -0.1700
Data Index: 6514725 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3018. Min Act: -0.1700
Data Index: 4488844 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3018. Min Act: -0.1700
Data Index: 6252572 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2705. Min Act: -0.1700
Data Index: 431971 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2705. Min Act: -0.1700
Data Index: 3061099 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2393. Min Act: -0.1700
Data Index: 3259232 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2393. Min Act: -0.1700
Data Index: 647859 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2393. Min Act: -0.1700
Data Index: 8091775 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2393. Min Act: -0.1700
Data Index: 8652583 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.2080. Min Act: -0.1700
Data Index: 6681459 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19