Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2297. Min Range: -3.2297
Max Act: 3.2297. Min Act: -0.1700
Data Index: 2181516 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2297. Min Range: -3.2297
Max Act: 3.1510. Min Act: -0.1700
Data Index: 3717917 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2297. Min Range: -3.2297
Max Act: 3.0249. Min Act: -0.1700
Data Index: 5836336 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2297. Min Range: -3.2297
Max Act: 3.0091. Min Act: -0.1700
Data Index: 6133878 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9775. Min Act: -0.1700
Data Index: 5433648 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9617. Min Act: -0.1700
Data Index: 3767567 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9300. Min Act: -0.1700
Data Index: 5103185 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9142. Min Act: -0.1700
Data Index: 2452945 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9300. Min Act: -0.1700
Data Index: 1450696 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9300. Min Act: -0.1700
Data Index: 7698474 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9142. Min Act: -0.1700
Data Index: 5655136 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9142. Min Act: -0.1700
Data Index: 4342010 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9300. Min Act: -0.1700
Data Index: 8639443 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9142. Min Act: -0.1700
Data Index: 5200382 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.9142. Min Act: -0.1700
Data Index: 8152071 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.8983. Min Act: -0.1700
Data Index: 4252131 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.8824. Min Act: -0.1700
Data Index: 405223 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.8983. Min Act: -0.1700
Data Index: 2820398 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.8983. Min Act: -0.1700
Data Index: 755647 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2297. Min Range: -3.2297
Max Act: 2.8824. Min Act: -0.1700
Data Index: 8010248 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19