Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1965 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2437. Min Range: -7.2437
Max Act: 7.2437. Min Act: -0.1700
Data Index: 1612890 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.9624. Min Act: -0.1700
Data Index: 1408278 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.8999. Min Act: -0.1700
Data Index: 6487380 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.8374. Min Act: -0.1700
Data Index: 562144 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.7749. Min Act: -0.1700
Data Index: 309702 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.7749. Min Act: -0.1700
Data Index: 5176738 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.7437. Min Act: -0.1700
Data Index: 1759950 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.6499. Min Act: -0.1700
Data Index: 770186 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.6499. Min Act: -0.1700
Data Index: 2369183 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.6187. Min Act: -0.1700
Data Index: 5834559 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.5562. Min Act: -0.1700
Data Index: 6014783 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.5562. Min Act: -0.1700
Data Index: 4690126 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.5249. Min Act: -0.1700
Data Index: 4900478 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.5249. Min Act: -0.1700
Data Index: 3138382 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.4937. Min Act: -0.1700
Data Index: 2102503 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.4312. Min Act: -0.1700
Data Index: 3978077 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.4312. Min Act: -0.1700
Data Index: 1759952 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.4624. Min Act: -0.1700
Data Index: 7699672 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.4312. Min Act: -0.1700
Data Index: 1128363 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2437. Min Range: -7.2437
Max Act: 6.4312. Min Act: -0.1700
Data Index: 3325067 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19