Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.4025. Min Act: -0.1700
Data Index: 454148 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.3400. Min Act: -0.1700
Data Index: 1991718 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.2775. Min Act: -0.1700
Data Index: 6238554 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.2775. Min Act: -0.1700
Data Index: 2912070 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.2150. Min Act: -0.1700
Data Index: 2814360 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.2150. Min Act: -0.1700
Data Index: 3136958 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.1525. Min Act: -0.1700
Data Index: 2842380 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.1525. Min Act: -0.1700
Data Index: 5314026 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.0900. Min Act: -0.1700
Data Index: 8551738 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.0900. Min Act: -0.1700
Data Index: 284175 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4025. Min Range: -9.4025
Max Act: 9.0275. Min Act: -0.1700
Data Index: 6295154 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9650. Min Act: -0.1700
Data Index: 1810867 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9650. Min Act: -0.1700
Data Index: 7969933 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9650. Min Act: -0.1700
Data Index: 3397459 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9025. Min Act: -0.1700
Data Index: 4427589 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9025. Min Act: -0.1700
Data Index: 4760617 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9025. Min Act: -0.1700
Data Index: 3491724 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9025. Min Act: -0.1700
Data Index: 7921232 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9025. Min Act: -0.1700
Data Index: 5798372 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4025. Min Range: -9.4025
Max Act: 8.9025. Min Act: -0.1700
Data Index: 2591663 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19