Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0546. Min Range: -7.0546
Max Act: 7.0546. Min Act: -0.1700
Data Index: 308798 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.9608. Min Act: -0.1700
Data Index: 5911718 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.8046. Min Act: -0.1700
Data Index: 5082193 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.7733. Min Act: -0.1700
Data Index: 642302 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.6796. Min Act: -0.1700
Data Index: 1461422 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.6796. Min Act: -0.1700
Data Index: 2640852 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.6483. Min Act: -0.1700
Data Index: 2695976 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.6171. Min Act: -0.1700
Data Index: 1586767 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.5858. Min Act: -0.1700
Data Index: 1081581 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.6171. Min Act: -0.1700
Data Index: 7537272 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.5858. Min Act: -0.1700
Data Index: 4363893 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.5546. Min Act: -0.1700
Data Index: 8392650 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.5233. Min Act: -0.1700
Data Index: 6544251 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.5233. Min Act: -0.1700
Data Index: 3533273 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.4921. Min Act: -0.1700
Data Index: 4058032 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.5233. Min Act: -0.1700
Data Index: 2991856 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.4921. Min Act: -0.1700
Data Index: 85822 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.4296. Min Act: -0.1700
Data Index: 2335071 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.4608. Min Act: -0.1700
Data Index: 3153103 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0546. Min Range: -7.0546
Max Act: 6.3983. Min Act: -0.1700
Data Index: 6788483 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19