Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3995. Min Act: -0.1700
Data Index: 1868151 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3668. Min Act: -0.1700
Data Index: 2443093 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3341. Min Act: -0.1700
Data Index: 4689253 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3505. Min Act: -0.1700
Data Index: 1885382 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3341. Min Act: -0.1698
Data Index: 2931481 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3341. Min Act: -0.1699
Data Index: 7738557 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3176. Min Act: -0.1700
Data Index: 279183 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3176. Min Act: -0.1700
Data Index: 7478952 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3176. Min Act: -0.1700
Data Index: 2815822 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3012. Min Act: -0.1700
Data Index: 3843857 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3012. Min Act: -0.1700
Data Index: 1211237 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.3012. Min Act: -0.1700
Data Index: 3481136 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2847. Min Act: -0.1700
Data Index: 7854295 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2847. Min Act: -0.1700
Data Index: 6289587 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2847. Min Act: -0.1700
Data Index: 5344193 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2847. Min Act: -0.1700
Data Index: 4620437 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2683. Min Act: -0.1700
Data Index: 7499132 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2683. Min Act: -0.1700
Data Index: 7352073 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2517. Min Act: -0.1700
Data Index: 2059714 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3995. Min Range: -2.3995
Max Act: 2.2683. Min Act: -0.1700
Data Index: 1669591 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19