Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.6217. Min Act: -0.1700
Data Index: 8030735 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.5904. Min Act: -0.1700
Data Index: 469420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4967. Min Act: -0.1700
Data Index: 8101033 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.5279. Min Act: -0.1700
Data Index: 3980340 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.5279. Min Act: -0.1700
Data Index: 1636057 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.5279. Min Act: -0.1700
Data Index: 1046010 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4967. Min Act: -0.1700
Data Index: 6189068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4967. Min Act: -0.1700
Data Index: 6344686 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4967. Min Act: -0.1700
Data Index: 4361050 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4654. Min Act: -0.1700
Data Index: 7408457 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4654. Min Act: -0.1700
Data Index: 2055152 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4654. Min Act: -0.1700
Data Index: 3335365 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4654. Min Act: -0.1700
Data Index: 5864547 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4342. Min Act: -0.1700
Data Index: 1896741 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4654. Min Act: -0.1700
Data Index: 2481761 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4654. Min Act: -0.1700
Data Index: 3998083 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4342. Min Act: -0.1700
Data Index: 4813192 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4342. Min Act: -0.1700
Data Index: 3952043 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4342. Min Act: -0.1700
Data Index: 4445072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6217. Min Range: -4.6217
Max Act: 4.4029. Min Act: -0.1700
Data Index: 5485166 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19