Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.7134. Min Act: -0.1700
Data Index: 6803258 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.7134. Min Act: -0.1700
Data Index: 8270443 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.6822. Min Act: -0.1700
Data Index: 606131 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.6509. Min Act: -0.1700
Data Index: 4827315 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.6197. Min Act: -0.1700
Data Index: 6620738 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.6197. Min Act: -0.1700
Data Index: 565494 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.6197. Min Act: -0.1700
Data Index: 1218046 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.5572. Min Act: -0.1700
Data Index: 6961704 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.5259. Min Act: -0.1700
Data Index: 998201 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4947. Min Act: -0.1700
Data Index: 2954827 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4947. Min Act: -0.1700
Data Index: 3541560 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4947. Min Act: -0.1700
Data Index: 2979205 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4634. Min Act: -0.1700
Data Index: 1535899 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4322. Min Act: -0.1700
Data Index: 2681590 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4009. Min Act: -0.1700
Data Index: 2681565 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4009. Min Act: -0.1700
Data Index: 1994757 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4009. Min Act: -0.1700
Data Index: 5663 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4009. Min Act: -0.1700
Data Index: 3654540 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.4009. Min Act: -0.1700
Data Index: 2480006 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7134. Min Range: -4.7134
Max Act: 4.3697. Min Act: -0.1700
Data Index: 1245824 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19