Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8631. Min Act: -0.1700
Data Index: 2642235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8318. Min Act: -0.1700
Data Index: 5772321 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8318. Min Act: -0.1700
Data Index: 45078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8318. Min Act: -0.1700
Data Index: 5022811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8006. Min Act: -0.1700
Data Index: 2949615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8006. Min Act: -0.1700
Data Index: 6268101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8006. Min Act: -0.1700
Data Index: 4832616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7693. Min Act: -0.1700
Data Index: 3901458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7067. Min Act: -0.1700
Data Index: 206769 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7067. Min Act: -0.1700
Data Index: 6676519 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7067. Min Act: -0.1700
Data Index: 5999315 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 3354967 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 6960357 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6754. Min Act: -0.1700
Data Index: 586602 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 3445542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6754. Min Act: -0.1700
Data Index: 5800042 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 2065467 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 1779545 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 1503056 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6129. Min Act: -0.1700
Data Index: 96331 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19