Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4893 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3646. Min Act: -0.1700
Data Index: 5247860 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 3337247 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 2035415 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3646. Min Act: -0.1700
Data Index: 6429817 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 4379812 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 7960541 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 5581635 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 4040553 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.2708. Min Act: -0.1700
Data Index: 1935285 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.2708. Min Act: -0.1700
Data Index: 3610788 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.2083. Min Act: -0.1700
Data Index: 68702 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7823742 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1771. Min Act: -0.1700
Data Index: 7525671 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1771. Min Act: -0.1700
Data Index: 2375580 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1458. Min Act: -0.1700
Data Index: 6843397 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1458. Min Act: -0.1700
Data Index: 5800076 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1458. Min Act: -0.1700
Data Index: 5030968 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1146. Min Act: -0.1700
Data Index: 6316233 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.1146. Min Act: -0.1700
Data Index: 7672209 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.0833. Min Act: -0.1700
Data Index: 462950 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19