Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 719 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.9958. Min Act: -0.1700
Data Index: 2817864 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.4333. Min Act: -0.1700
Data Index: 122912 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.3395. Min Act: -0.1700
Data Index: 4977404 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.3395. Min Act: -0.1700
Data Index: 1211960 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.3395. Min Act: -0.1700
Data Index: 3626457 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.3395. Min Act: -0.1700
Data Index: 6742881 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.2770. Min Act: -0.1700
Data Index: 8059592 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.2770. Min Act: -0.1700
Data Index: 6940311 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.2145. Min Act: -0.1700
Data Index: 3772260 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.1833. Min Act: -0.1700
Data Index: 5473275 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.1833. Min Act: -0.1700
Data Index: 2801537 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.1833. Min Act: -0.1700
Data Index: 2801533 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.1208. Min Act: -0.1700
Data Index: 4288562 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.1520. Min Act: -0.1700
Data Index: 7740917 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.1208. Min Act: -0.1700
Data Index: 2493824 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.0895. Min Act: -0.1700
Data Index: 8464710 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.0583. Min Act: -0.1700
Data Index: 5293235 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.0270. Min Act: -0.1700
Data Index: 4857523 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.0270. Min Act: -0.1700
Data Index: 2578454 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9958. Min Range: -7.9958
Max Act: 7.0270. Min Act: -0.1700
Data Index: 3326832 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19