Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.9972. Min Act: -0.1700
Data Index: 6200056 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.6689. Min Act: -0.1700
Data Index: 5922660 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.6063. Min Act: -0.1700
Data Index: 7699007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.6063. Min Act: -0.1700
Data Index: 8658192 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.6063. Min Act: -0.1700
Data Index: 3736294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5906. Min Act: -0.1700
Data Index: 5607982 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5906. Min Act: -0.1700
Data Index: 8661140 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5906. Min Act: -0.1700
Data Index: 1290080 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5593. Min Act: -0.1700
Data Index: 5944658 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5437. Min Act: -0.1700
Data Index: 5454039 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5437. Min Act: -0.1700
Data Index: 4911796 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5437. Min Act: -0.1700
Data Index: 8032014 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5124. Min Act: -0.1700
Data Index: 2668504 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5280. Min Act: -0.1700
Data Index: 5122837 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.4967. Min Act: -0.1700
Data Index: 2493843 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.5124. Min Act: -0.1700
Data Index: 7396434 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.4967. Min Act: -0.1700
Data Index: 5827966 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.4810. Min Act: -0.1700
Data Index: 6768296 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.4654. Min Act: -0.1700
Data Index: 8055876 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9972. Min Range: -3.9972
Max Act: 3.4810. Min Act: -0.1700
Data Index: 2392434 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19