Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.5002. Min Act: -0.1700
Data Index: 3473848 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.4846. Min Act: -0.1700
Data Index: 1982245 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.5002. Min Act: -0.1700
Data Index: 5389554 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.4689. Min Act: -0.1700
Data Index: 5686331 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.4376. Min Act: -0.1700
Data Index: 6211754 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.4219. Min Act: -0.1700
Data Index: 3458362 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3749. Min Act: -0.1700
Data Index: 6104624 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3749. Min Act: -0.1700
Data Index: 7833776 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3592. Min Act: -0.1700
Data Index: 4286543 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3592. Min Act: -0.1700
Data Index: 1402622 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3435. Min Act: -0.1700
Data Index: 3962829 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3121. Min Act: -0.1700
Data Index: 1727945 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3278. Min Act: -0.1700
Data Index: 5301927 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3121. Min Act: -0.1700
Data Index: 6439671 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3121. Min Act: -0.1700
Data Index: 498208 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3121. Min Act: -0.1700
Data Index: 8110339 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.3121. Min Act: -0.1700
Data Index: 1490832 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.2964. Min Act: -0.1700
Data Index: 5897753 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.2964. Min Act: -0.1700
Data Index: 7596257 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5002. Min Range: -3.5002
Max Act: 3.2807. Min Act: -0.1700
Data Index: 4999744 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19