Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5934 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0016. Min Range: -6.0016
Max Act: 6.0016. Min Act: -0.1700
Data Index: 2108987 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.8141. Min Act: -0.1700
Data Index: 6044201 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.7829. Min Act: -0.1700
Data Index: 330795 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.7204. Min Act: -0.1700
Data Index: 6169901 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.5954. Min Act: -0.1700
Data Index: 8323566 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.5329. Min Act: -0.1700
Data Index: 4139738 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.5016. Min Act: -0.1700
Data Index: 5049105 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.5016. Min Act: -0.1700
Data Index: 8777152 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.4391. Min Act: -0.1700
Data Index: 8352138 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.4391. Min Act: -0.1700
Data Index: 5049100 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.4391. Min Act: -0.1699
Data Index: 2489264 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.4391. Min Act: -0.1700
Data Index: 2877518 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 6292521 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5566117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 7732399 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3766. Min Act: -0.1692
Data Index: 4462603 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 6173466 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3766. Min Act: -0.1700
Data Index: 4136787 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3454. Min Act: -0.1700
Data Index: 4136788 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0016. Min Range: -6.0016
Max Act: 5.3141. Min Act: -0.1700
Data Index: 5051478 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19