Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5378 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.4939. Min Act: -0.1700
Data Index: 629216 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1189. Min Act: -0.1700
Data Index: 629215 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.9314. Min Act: -0.1700
Data Index: 675273 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.9314. Min Act: -0.1700
Data Index: 1145646 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3356157 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2225376 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.7439. Min Act: -0.1700
Data Index: 7397153 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 4423033 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 7786983 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 5992555 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2594541 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.6814. Min Act: -0.1700
Data Index: 444449 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.5877. Min Act: -0.1700
Data Index: 7770476 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.5877. Min Act: -0.1700
Data Index: 7377683 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.4939. Min Act: -0.1700
Data Index: 498364 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.4939. Min Act: -0.1700
Data Index: 2285667 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.4627. Min Act: -0.1700
Data Index: 3811247 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.4314. Min Act: -0.1700
Data Index: 6153509 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.4314. Min Act: -0.1700
Data Index: 2205522 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4939. Min Range: -6.4939
Max Act: 5.4314. Min Act: -0.1700
Data Index: 8676702 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19