Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1086 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.8689. Min Act: -0.1700
Data Index: 1602255 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7751. Min Act: -0.1700
Data Index: 3265354 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7438. Min Act: -0.1700
Data Index: 3998626 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7438. Min Act: -0.1700
Data Index: 1298477 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7438. Min Act: -0.1700
Data Index: 876638 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7438. Min Act: -0.1700
Data Index: 4809341 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7126. Min Act: -0.1700
Data Index: 8150788 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.7126. Min Act: -0.1700
Data Index: 7683771 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6813. Min Act: -0.1700
Data Index: 8438353 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6500. Min Act: -0.1700
Data Index: 3382611 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6500. Min Act: -0.1700
Data Index: 2000792 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6500. Min Act: -0.1700
Data Index: 4712546 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6813. Min Act: -0.1700
Data Index: 6557278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6813. Min Act: -0.1700
Data Index: 6013022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6813. Min Act: -0.1700
Data Index: 5647710 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6500. Min Act: -0.1700
Data Index: 7677996 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6500. Min Act: -0.1700
Data Index: 1956145 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6813. Min Act: -0.1700
Data Index: 4880618 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6187. Min Act: -0.1700
Data Index: 6991610 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8689. Min Range: -3.8689
Max Act: 3.6500. Min Act: -0.1700
Data Index: 89009 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19