Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.5571. Min Act: -0.1700
Data Index: 3155582 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4944. Min Act: -0.1700
Data Index: 6757459 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4788. Min Act: -0.1700
Data Index: 7163099 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4631. Min Act: -0.1700
Data Index: 1160378 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4631. Min Act: -0.1700
Data Index: 988554 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4631. Min Act: -0.1700
Data Index: 6153661 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4474. Min Act: -0.1700
Data Index: 6108176 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4161. Min Act: -0.1700
Data Index: 5324235 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.4161. Min Act: -0.1700
Data Index: 5504158 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3847. Min Act: -0.1700
Data Index: 7326892 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3847. Min Act: -0.1700
Data Index: 1991674 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3847. Min Act: -0.1700
Data Index: 7821810 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3847. Min Act: -0.1700
Data Index: 8702229 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3847. Min Act: -0.1700
Data Index: 3797853 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3691. Min Act: -0.1700
Data Index: 3358838 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3534. Min Act: -0.1700
Data Index: 7500628 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3377. Min Act: -0.1700
Data Index: 3691992 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3691. Min Act: -0.1700
Data Index: 1878957 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3377. Min Act: -0.1700
Data Index: 3094970 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5571. Min Range: -3.5571
Max Act: 3.3220. Min Act: -0.1700
Data Index: 7390761 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19