Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.3550. Min Act: -0.1700
Data Index: 6257573 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.2925. Min Act: -0.1700
Data Index: 3741011 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.1987. Min Act: -0.1700
Data Index: 5374819 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.0425. Min Act: -0.1700
Data Index: 7588953 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.0425. Min Act: -0.1700
Data Index: 6544393 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.0425. Min Act: -0.1700
Data Index: 896992 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.0112. Min Act: -0.1700
Data Index: 1160839 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 5136315 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 8564643 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 2027957 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 6552498 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9487. Min Act: -0.1700
Data Index: 5750721 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9175. Min Act: -0.1700
Data Index: 2625677 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4900015 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9487. Min Act: -0.1700
Data Index: 1170117 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4086383 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8862. Min Act: -0.1700
Data Index: 3691380 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8550. Min Act: -0.1700
Data Index: 8019395 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8237. Min Act: -0.1700
Data Index: 181224 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8862. Min Act: -0.1700
Data Index: 8094176 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19