Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.2958. Min Act: -0.1700
Data Index: 538767 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.2645. Min Act: -0.1700
Data Index: 333092 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.2020. Min Act: -0.1700
Data Index: 5143066 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 6514516 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 7097802 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 1097445 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 6232195 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1697
Data Index: 1369927 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 5883787 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3797730 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1708. Min Act: -0.1700
Data Index: 1186269 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5296027 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 4145711 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5525997 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5258311 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1083. Min Act: -0.1700
Data Index: 3476950 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 6358959 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 2005212 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1395. Min Act: -0.1700
Data Index: 6475649 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2958. Min Range: -4.2958
Max Act: 4.1083. Min Act: -0.1700
Data Index: 1988699 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19