Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.8487. Min Act: -0.1700
Data Index: 6060438 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.7237. Min Act: -0.1700
Data Index: 3019506 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.6612. Min Act: -0.1700
Data Index: 3932931 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.5987. Min Act: -0.1700
Data Index: 2662229 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.5362. Min Act: -0.1700
Data Index: 6917871 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.5362. Min Act: -0.1700
Data Index: 6800708 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.5362. Min Act: -0.1700
Data Index: 5931837 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4737. Min Act: -0.1700
Data Index: 4248845 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4737. Min Act: -0.1700
Data Index: 6539896 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4737. Min Act: -0.1700
Data Index: 7811669 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4424. Min Act: -0.1700
Data Index: 3125408 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4424. Min Act: -0.1700
Data Index: 8819123 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 5877046 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 5549808 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 1322312 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 7189740 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.3799. Min Act: -0.1700
Data Index: 4840111 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 5244374 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.3487. Min Act: -0.1700
Data Index: 1134729 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8487. Min Range: -7.8487
Max Act: 7.3487. Min Act: -0.1700
Data Index: 4827586 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19