Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4684 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.6952. Min Act: -0.1700
Data Index: 2011285 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.5702. Min Act: -0.1700
Data Index: 2056744 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.5702. Min Act: -0.1700
Data Index: 1215505 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.4764. Min Act: -0.1700
Data Index: 2635092 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.4764. Min Act: -0.1700
Data Index: 7715554 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.3827. Min Act: -0.1700
Data Index: 7045458 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.4139. Min Act: -0.1700
Data Index: 2956679 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.2577. Min Act: -0.1700
Data Index: 5549112 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.2889. Min Act: -0.1700
Data Index: 1169813 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.2577. Min Act: -0.1700
Data Index: 7105322 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.2264. Min Act: -0.1700
Data Index: 2969548 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4548322 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.2264. Min Act: -0.1700
Data Index: 5285610 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1639. Min Act: -0.1700
Data Index: 3593457 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1639. Min Act: -0.1700
Data Index: 2954238 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1639. Min Act: -0.1700
Data Index: 1039596 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1639. Min Act: -0.1700
Data Index: 4155888 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1639. Min Act: -0.1700
Data Index: 5415735 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1639. Min Act: -0.1700
Data Index: 4268231 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6952. Min Range: -6.6952
Max Act: 6.1327. Min Act: -0.1700
Data Index: 3429471 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19