Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.9845. Min Act: -0.1700
Data Index: 3456384 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7970. Min Act: -0.1700
Data Index: 129791 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.8283. Min Act: -0.1700
Data Index: 2583468 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7658. Min Act: -0.1700
Data Index: 675604 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7658. Min Act: -0.1700
Data Index: 6491982 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7345. Min Act: -0.1700
Data Index: 7754878 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7033. Min Act: -0.1700
Data Index: 3086867 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7033. Min Act: -0.1700
Data Index: 6292577 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.7033. Min Act: -0.1700
Data Index: 111809 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.6408. Min Act: -0.1700
Data Index: 7238192 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.6408. Min Act: -0.1700
Data Index: 95961 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.6408. Min Act: -0.1700
Data Index: 5098994 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.6095. Min Act: -0.1700
Data Index: 4360422 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5470. Min Act: -0.1700
Data Index: 1289328 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5783. Min Act: -0.1700
Data Index: 2798321 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5470. Min Act: -0.1700
Data Index: 1170513 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5470. Min Act: -0.1700
Data Index: 1416826 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5158. Min Act: -0.1700
Data Index: 6587665 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5158. Min Act: -0.1700
Data Index: 3830974 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9845. Min Range: -6.9845
Max Act: 6.5470. Min Act: -0.1700
Data Index: 8254920 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19