Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4060 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.7985. Min Act: -0.1700
Data Index: 8345184 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.7672. Min Act: -0.1700
Data Index: 4147280 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.7047. Min Act: -0.1700
Data Index: 3198144 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.6422. Min Act: -0.1700
Data Index: 879744 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.6110. Min Act: -0.1700
Data Index: 3933350 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.6110. Min Act: -0.1700
Data Index: 6668929 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.5797. Min Act: -0.1700
Data Index: 2762336 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.5485. Min Act: -0.1700
Data Index: 4118628 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.5485. Min Act: -0.1700
Data Index: 7073280 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.5172. Min Act: -0.1700
Data Index: 7534417 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.4860. Min Act: -0.1700
Data Index: 6022557 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.4547. Min Act: -0.1700
Data Index: 7802282 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.4547. Min Act: -0.1700
Data Index: 584657 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.4235. Min Act: -0.1700
Data Index: 6377589 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.3922. Min Act: -0.1700
Data Index: 6996446 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.3922. Min Act: -0.1700
Data Index: 1086995 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.3922. Min Act: -0.1700
Data Index: 7073276 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.3922. Min Act: -0.1700
Data Index: 1115868 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.3922. Min Act: -0.1700
Data Index: 7432768 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7985. Min Range: -6.7985
Max Act: 6.3610. Min Act: -0.1700
Data Index: 5838394 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19