Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.8970. Min Act: -0.1700
Data Index: 631678 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.5845. Min Act: -0.1700
Data Index: 6217262 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.5220. Min Act: -0.1700
Data Index: 2731149 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4595. Min Act: -0.1700
Data Index: 2550565 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4907. Min Act: -0.1700
Data Index: 1881675 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4282. Min Act: -0.1700
Data Index: 2299582 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4282. Min Act: -0.1700
Data Index: 2385264 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4595. Min Act: -0.1700
Data Index: 4775890 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3970. Min Act: -0.1700
Data Index: 3439337 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3657. Min Act: -0.1700
Data Index: 3566775 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3970. Min Act: -0.1700
Data Index: 7347163 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3970. Min Act: -0.1700
Data Index: 6842942 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3970. Min Act: -0.1700
Data Index: 532336 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3657. Min Act: -0.1700
Data Index: 7522530 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3345. Min Act: -0.1700
Data Index: 8772110 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3657. Min Act: -0.1700
Data Index: 1524363 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3345. Min Act: -0.1700
Data Index: 8202744 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 934675 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3032. Min Act: -0.1700
Data Index: 8794257 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2407. Min Act: -0.1700
Data Index: 3298835 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19