Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5955 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.5593. Min Act: -0.1700
Data Index: 8185903 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.4968. Min Act: -0.1700
Data Index: 4043109 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.2780. Min Act: -0.1700
Data Index: 3294900 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.2468. Min Act: -0.1700
Data Index: 5065237 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.2155. Min Act: -0.1700
Data Index: 2078922 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.1843. Min Act: -0.1700
Data Index: 5789099 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.1530. Min Act: -0.1700
Data Index: 7919296 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.1530. Min Act: -0.1700
Data Index: 7084908 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.1530. Min Act: -0.1700
Data Index: 4826281 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.1218. Min Act: -0.1700
Data Index: 7185818 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.1218. Min Act: -0.1700
Data Index: 5419623 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0905. Min Act: -0.1700
Data Index: 4290987 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0905. Min Act: -0.1700
Data Index: 6161213 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0905. Min Act: -0.1700
Data Index: 8672412 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0592. Min Act: -0.1700
Data Index: 8260266 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0592. Min Act: -0.1700
Data Index: 4228683 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0592. Min Act: -0.1700
Data Index: 4148574 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0280. Min Act: -0.1700
Data Index: 508100 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5593. Min Range: -4.5593
Max Act: 3.9967. Min Act: -0.1700
Data Index: 4033411 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5593. Min Range: -4.5593
Max Act: 4.0280. Min Act: -0.1700
Data Index: 6987228 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19