Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6192 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.7503. Min Act: -0.1700
Data Index: 1120071 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.6878. Min Act: -0.1700
Data Index: 8339315 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.5003. Min Act: -0.1700
Data Index: 3436273 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.5003. Min Act: -0.1700
Data Index: 3561147 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.4690. Min Act: -0.1700
Data Index: 5735265 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.4378. Min Act: -0.1700
Data Index: 1212034 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.4065. Min Act: -0.1700
Data Index: 515496 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.3753. Min Act: -0.1700
Data Index: 6660564 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.3753. Min Act: -0.1700
Data Index: 3192259 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.3440. Min Act: -0.1700
Data Index: 5732070 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.3753. Min Act: -0.1700
Data Index: 4293492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2815. Min Act: -0.1700
Data Index: 7456604 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2503. Min Act: -0.1700
Data Index: 2411774 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2815. Min Act: -0.1700
Data Index: 7996429 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2503. Min Act: -0.1700
Data Index: 3117669 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2503. Min Act: -0.1700
Data Index: 2152830 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2190. Min Act: -0.1700
Data Index: 6891608 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2503. Min Act: -0.1700
Data Index: 2828283 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2190. Min Act: -0.1700
Data Index: 4019864 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7503. Min Range: -6.7503
Max Act: 6.2190. Min Act: -0.1700
Data Index: 5709129 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19