Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6053 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.7259. Min Act: -0.1700
Data Index: 7770444 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.7259. Min Act: -0.1700
Data Index: 496395 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.6947. Min Act: -0.1700
Data Index: 3343673 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.6322. Min Act: -0.1700
Data Index: 145469 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5697. Min Act: -0.1700
Data Index: 4083009 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5697. Min Act: -0.1700
Data Index: 6064748 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5384. Min Act: -0.1700
Data Index: 5700755 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5072. Min Act: -0.1700
Data Index: 4997128 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5072. Min Act: -0.1700
Data Index: 293511 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5072. Min Act: -0.1700
Data Index: 2573775 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5072. Min Act: -0.1700
Data Index: 2771545 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.5072. Min Act: -0.1700
Data Index: 1692202 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.4759. Min Act: -0.1700
Data Index: 76189 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.4447. Min Act: -0.1700
Data Index: 5720231 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.4447. Min Act: -0.1700
Data Index: 6393262 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.4134. Min Act: -0.1700
Data Index: 3062207 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.4134. Min Act: -0.1700
Data Index: 4083006 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.4134. Min Act: -0.1700
Data Index: 8375980 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.3822. Min Act: -0.1700
Data Index: 148622 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7259. Min Range: -5.7259
Max Act: 5.3822. Min Act: -0.1700
Data Index: 3104532 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19