Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4285 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.7445. Min Act: -0.1700
Data Index: 1364019 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.6195. Min Act: -0.1700
Data Index: 2883329 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.6820. Min Act: -0.1700
Data Index: 7115305 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4945. Min Act: -0.1700
Data Index: 4346842 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4945. Min Act: -0.1700
Data Index: 4765218 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4945. Min Act: -0.1700
Data Index: 8595127 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4945. Min Act: -0.1700
Data Index: 6143493 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4320. Min Act: -0.1700
Data Index: 6067756 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4320. Min Act: -0.1700
Data Index: 2668251 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4320. Min Act: -0.1700
Data Index: 1669561 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4320. Min Act: -0.1700
Data Index: 4606708 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.4320. Min Act: -0.1700
Data Index: 228867 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3695. Min Act: -0.1700
Data Index: 8370544 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3695. Min Act: -0.1700
Data Index: 4602513 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3695. Min Act: -0.1700
Data Index: 6034591 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3070. Min Act: -0.1700
Data Index: 1198889 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3695. Min Act: -0.1700
Data Index: 8180691 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3695. Min Act: -0.1700
Data Index: 7524317 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3695. Min Act: -0.1700
Data Index: 2705821 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7445. Min Range: -8.7445
Max Act: 8.3070. Min Act: -0.1700
Data Index: 7934444 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19