Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4109 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.4546. Min Act: -0.1700
Data Index: 4161319 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.3921. Min Act: -0.1700
Data Index: 6155846 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.2983. Min Act: -0.1700
Data Index: 7452021 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.2046. Min Act: -0.1700
Data Index: 40020 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.1108. Min Act: -0.1700
Data Index: 4664896 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.0796. Min Act: -0.1700
Data Index: 5745450 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.0171. Min Act: -0.1700
Data Index: 6925635 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4546. Min Range: -7.4546
Max Act: 7.0171. Min Act: -0.1700
Data Index: 4335785 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9858. Min Act: -0.1700
Data Index: 5426321 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9858. Min Act: -0.1700
Data Index: 8532455 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9233. Min Act: -0.1700
Data Index: 8441928 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9546. Min Act: -0.1700
Data Index: 4846337 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9546. Min Act: -0.1700
Data Index: 3464760 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9546. Min Act: -0.1700
Data Index: 7025377 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9233. Min Act: -0.1700
Data Index: 3453849 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9233. Min Act: -0.1700
Data Index: 1634814 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.9233. Min Act: -0.1700
Data Index: 6926752 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.8921. Min Act: -0.1700
Data Index: 1868033 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.8296. Min Act: -0.1700
Data Index: 5478233 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4546. Min Range: -7.4546
Max Act: 6.8296. Min Act: -0.1700
Data Index: 2063535 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19