Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4965. Min Range: -7.4965
Max Act: 7.4965. Min Act: -0.1700
Data Index: 2555252 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.7465. Min Act: -0.1700
Data Index: 2455630 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6840. Min Act: -0.1700
Data Index: 5337664 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6527. Min Act: -0.1700
Data Index: 6089835 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.6840. Min Act: -0.1700
Data Index: 685504 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.5590. Min Act: -0.1700
Data Index: 2427052 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.5902. Min Act: -0.1700
Data Index: 685503 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4652. Min Act: -0.1700
Data Index: 2328547 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4652. Min Act: -0.1700
Data Index: 4373028 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4340. Min Act: -0.1700
Data Index: 2555225 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4340. Min Act: -0.1700
Data Index: 2555251 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4340. Min Act: -0.1700
Data Index: 8371993 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4652. Min Act: -0.1700
Data Index: 2555250 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4027. Min Act: -0.1700
Data Index: 5554289 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4027. Min Act: -0.1698
Data Index: 6883888 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.4027. Min Act: -0.1700
Data Index: 2555253 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.3715. Min Act: -0.1700
Data Index: 2555235 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.3402. Min Act: -0.1700
Data Index: 2611686 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.3090. Min Act: -0.1700
Data Index: 6331319 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4965. Min Range: -7.4965
Max Act: 6.3402. Min Act: -0.1700
Data Index: 846959 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19