Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5999. Min Act: -0.1700
Data Index: 8431593 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5687. Min Act: -0.1700
Data Index: 4878733 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5687. Min Act: -0.1700
Data Index: 7059376 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5600256 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 534 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7763598 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5062. Min Act: -0.1700
Data Index: 1135944 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7709308 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 378357 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7515514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 5755294 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 5602786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3499314 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 5562649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 5469523 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 688590 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 4737318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 4447803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3933535 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5999. Min Range: -4.5999
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3865317 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19