Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 674 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.4198. Min Act: -0.1700
Data Index: 7702723 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.4042. Min Act: -0.1700
Data Index: 1752772 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.4042. Min Act: -0.1700
Data Index: 4927678 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3885. Min Act: -0.1700
Data Index: 4583206 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3885. Min Act: -0.1700
Data Index: 7357178 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3728. Min Act: -0.1700
Data Index: 7834913 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 1279044 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3885. Min Act: -0.1700
Data Index: 6197067 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3728. Min Act: -0.1700
Data Index: 4340848 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3728. Min Act: -0.1700
Data Index: 3820803 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 2741084 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3728. Min Act: -0.1700
Data Index: 5561099 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3728. Min Act: -0.1700
Data Index: 850229 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 422747 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 4956950 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 4054876 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3414. Min Act: -0.1700
Data Index: 197167 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 3930818 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3414. Min Act: -0.1700
Data Index: 3497165 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4198. Min Range: -3.4198
Max Act: 3.3571. Min Act: -0.1700
Data Index: 3321765 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19