Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.4888. Min Act: -0.1700
Data Index: 618 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3951. Min Act: -0.1700
Data Index: 6922877 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.4263. Min Act: -0.1700
Data Index: 3608278 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3638. Min Act: -0.1700
Data Index: 4019643 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3951. Min Act: -0.1700
Data Index: 2359966 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3638. Min Act: -0.1700
Data Index: 3583384 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3638. Min Act: -0.1700
Data Index: 7332893 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3326. Min Act: -0.1700
Data Index: 7513331 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3951. Min Act: -0.1700
Data Index: 361230 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3326. Min Act: -0.1700
Data Index: 3899810 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3326. Min Act: -0.1700
Data Index: 2359550 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3326. Min Act: -0.1700
Data Index: 4670250 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3326. Min Act: -0.1700
Data Index: 458542 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3013. Min Act: -0.1700
Data Index: 297237 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3013. Min Act: -0.1700
Data Index: 4944513 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3326. Min Act: -0.1700
Data Index: 8508578 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3013. Min Act: -0.1700
Data Index: 4419326 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3013. Min Act: -0.1700
Data Index: 896459 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2701. Min Act: -0.1700
Data Index: 2055167 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2701. Min Act: -0.1700
Data Index: 3770135 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19