Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.7954. Min Act: -0.1700
Data Index: 5701406 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.5454. Min Act: -0.1700
Data Index: 3433918 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.4204. Min Act: -0.1700
Data Index: 649489 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.3267. Min Act: -0.1700
Data Index: 2764538 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2954. Min Act: -0.1700
Data Index: 591613 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.3267. Min Act: -0.1700
Data Index: 614123 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2954. Min Act: -0.1700
Data Index: 6476169 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2329. Min Act: -0.1700
Data Index: 6594202 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2017. Min Act: -0.1700
Data Index: 636061 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2017. Min Act: -0.1700
Data Index: 4436591 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2017. Min Act: -0.1700
Data Index: 8770153 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.1392. Min Act: -0.1700
Data Index: 2149329 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.1704. Min Act: -0.1700
Data Index: 1273877 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.1392. Min Act: -0.1700
Data Index: 4659476 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.1079. Min Act: -0.1700
Data Index: 3696230 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.1079. Min Act: -0.1700
Data Index: 1433392 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0767. Min Act: -0.1700
Data Index: 4402061 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0767. Min Act: -0.1700
Data Index: 5670035 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0767. Min Act: -0.1700
Data Index: 7029406 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0454. Min Act: -0.1700
Data Index: 1072109 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19