Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.6569. Min Act: -0.1700
Data Index: 8314080 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.6569. Min Act: -0.1700
Data Index: 1416491 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.5319. Min Act: -0.1700
Data Index: 3279839 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.5319. Min Act: -0.1700
Data Index: 4526945 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.4069. Min Act: -0.1700
Data Index: 8614710 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.4069. Min Act: -0.1700
Data Index: 8313041 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.3444. Min Act: -0.1700
Data Index: 5996709 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.2819. Min Act: -0.1700
Data Index: 1912845 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.2819. Min Act: -0.1700
Data Index: 3881612 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.2194. Min Act: -0.1700
Data Index: 1495132 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.2194. Min Act: -0.1700
Data Index: 4409329 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.2194. Min Act: -0.1700
Data Index: 699293 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.1569. Min Act: -0.1700
Data Index: 1744515 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.1569. Min Act: -0.1700
Data Index: 2670530 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.1569. Min Act: -0.1700
Data Index: 7440152 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.0944. Min Act: -0.1700
Data Index: 4338103 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6569. Min Range: -9.6569
Max Act: 8.9694. Min Act: -0.1700
Data Index: 1037357 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.0319. Min Act: -0.1700
Data Index: 1434358 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6569. Min Range: -9.6569
Max Act: 8.9694. Min Act: -0.1700
Data Index: 5575671 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6569. Min Range: -9.6569
Max Act: 9.0319. Min Act: -0.1700
Data Index: 2462484 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19