Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3852. Min Range: -6.3852
Max Act: 6.3852. Min Act: -0.1700
Data Index: 3229629 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3852. Min Range: -6.3852
Max Act: 6.1352. Min Act: -0.1700
Data Index: 8327363 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3852. Min Range: -6.3852
Max Act: 6.1352. Min Act: -0.1700
Data Index: 6399714 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3852. Min Range: -6.3852
Max Act: 6.0415. Min Act: -0.1700
Data Index: 5631845 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3852. Min Range: -6.3852
Max Act: 6.0102. Min Act: -0.1700
Data Index: 7404979 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3852. Min Range: -6.3852
Max Act: 6.0102. Min Act: -0.1700
Data Index: 8408383 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.9165. Min Act: -0.1700
Data Index: 2684821 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.8852. Min Act: -0.1700
Data Index: 6500133 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3144389 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.8540. Min Act: -0.1700
Data Index: 3781003 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.8540. Min Act: -0.1700
Data Index: 2780540 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8530951 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.8227. Min Act: -0.1700
Data Index: 6168627 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.7915. Min Act: -0.1700
Data Index: 7709343 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.7915. Min Act: -0.1700
Data Index: 4444859 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.6977. Min Act: -0.1700
Data Index: 3887 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4773555 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.7290. Min Act: -0.1700
Data Index: 6190695 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4113762 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3852. Min Range: -6.3852
Max Act: 5.6665. Min Act: -0.1700
Data Index: 268389 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19