Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1597 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.9571. Min Act: -0.1700
Data Index: 466547 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.6133. Min Act: -0.1700
Data Index: 6064717 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.6133. Min Act: -0.1700
Data Index: 3070685 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.4258. Min Act: -0.1700
Data Index: 4604656 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.4258. Min Act: -0.1700
Data Index: 2941837 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3946. Min Act: -0.1700
Data Index: 5837160 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.4258. Min Act: -0.1700
Data Index: 8052628 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3946. Min Act: -0.1700
Data Index: 6948754 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3321. Min Act: -0.1700
Data Index: 3315664 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3008. Min Act: -0.1700
Data Index: 6104670 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3321. Min Act: -0.1700
Data Index: 3400783 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3321. Min Act: -0.1700
Data Index: 1340844 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3321. Min Act: -0.1700
Data Index: 6138707 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3008. Min Act: -0.1700
Data Index: 8375048 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3008. Min Act: -0.1700
Data Index: 5009103 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3008. Min Act: -0.1700
Data Index: 6744675 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.3008. Min Act: -0.1700
Data Index: 7940393 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.2383. Min Act: -0.1700
Data Index: 8025496 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.2696. Min Act: -0.1700
Data Index: 8439169 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9571. Min Range: -5.9571
Max Act: 5.2696. Min Act: -0.1700
Data Index: 1801055 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19