Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4431. Min Range: -8.4431
Max Act: 8.4431. Min Act: -0.1700
Data Index: 8016608 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4431. Min Range: -8.4431
Max Act: 8.2556. Min Act: -0.1700
Data Index: 8178648 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.9744. Min Act: -0.1700
Data Index: 7629075 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.9119. Min Act: -0.1700
Data Index: 6712583 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.8806. Min Act: -0.1700
Data Index: 788943 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.8494. Min Act: -0.1700
Data Index: 4178598 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.7869. Min Act: -0.1700
Data Index: 3431808 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.7869. Min Act: -0.1700
Data Index: 6824926 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.7556. Min Act: -0.1700
Data Index: 4387806 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.7244. Min Act: -0.1700
Data Index: 4714203 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.6931. Min Act: -0.1700
Data Index: 7666097 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.7244. Min Act: -0.1700
Data Index: 4807820 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.6931. Min Act: -0.1700
Data Index: 7268301 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.6931. Min Act: -0.1700
Data Index: 1599345 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.5681. Min Act: -0.1700
Data Index: 86127 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.5681. Min Act: -0.1700
Data Index: 8671619 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.5681. Min Act: -0.1700
Data Index: 3139995 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.5681. Min Act: -0.1700
Data Index: 6477217 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.5369. Min Act: -0.1700
Data Index: 3298708 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4431. Min Range: -8.4431
Max Act: 7.5369. Min Act: -0.1700
Data Index: 5798822 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19