Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4724 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1690
Data Index: 5491337 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 795630 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1699
Data Index: 1312343 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 8471223 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 4968998 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 1608103 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 4462530 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 6429561 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1699
Data Index: 5383817 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 7700125 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1699
Data Index: 7009343 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1699
Data Index: 8463248 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 3846119 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1699
Data Index: 6105939 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 5891282 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 815226 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1694
Data Index: 7740170 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 614320 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.7934. Min Act: -0.1700
Data Index: 5414500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.7309. Min Act: -0.1700
Data Index: 3235431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19