Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5261 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.5697. Min Act: -0.1700
Data Index: 8086218 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.4760. Min Act: -0.1700
Data Index: 8198981 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.4447. Min Act: -0.1700
Data Index: 3167915 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.4135. Min Act: -0.1700
Data Index: 8198982 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.3510. Min Act: -0.1700
Data Index: 8092351 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2885. Min Act: -0.1700
Data Index: 1105266 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2885. Min Act: -0.1700
Data Index: 7945425 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.3510. Min Act: -0.1700
Data Index: 3853531 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5445039 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2885. Min Act: -0.1700
Data Index: 6513212 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2885. Min Act: -0.1700
Data Index: 3727004 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2572. Min Act: -0.1700
Data Index: 543462 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2572. Min Act: -0.1700
Data Index: 3881423 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2572. Min Act: -0.1700
Data Index: 51029 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2572. Min Act: -0.1700
Data Index: 6592827 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2572. Min Act: -0.1700
Data Index: 5295575 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2572. Min Act: -0.1700
Data Index: 6468261 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.2260. Min Act: -0.1700
Data Index: 368708 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.1947. Min Act: -0.1700
Data Index: 8031026 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5697. Min Range: -5.5697
Max Act: 5.1947. Min Act: -0.1700
Data Index: 8659759 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19