Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 311 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.5956. Min Act: -0.1700
Data Index: 3483671 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.5644. Min Act: -0.1700
Data Index: 1192672 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.4394. Min Act: -0.1700
Data Index: 3250278 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.5019. Min Act: -0.1700
Data Index: 4983455 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.4394. Min Act: -0.1700
Data Index: 5059604 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.4081. Min Act: -0.1700
Data Index: 1244085 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.4394. Min Act: -0.1700
Data Index: 5037126 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3456. Min Act: -0.1700
Data Index: 7619518 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3456. Min Act: -0.1700
Data Index: 6228624 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2831. Min Act: -0.1700
Data Index: 6785518 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3456. Min Act: -0.1700
Data Index: 3001144 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3456. Min Act: -0.1700
Data Index: 5468712 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3144. Min Act: -0.1700
Data Index: 8562080 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3144. Min Act: -0.1700
Data Index: 6144213 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2519. Min Act: -0.1700
Data Index: 3448722 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.3144. Min Act: -0.1700
Data Index: 4241448 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2831. Min Act: -0.1700
Data Index: 2929615 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2831. Min Act: -0.1700
Data Index: 4710429 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2206. Min Act: -0.1700
Data Index: 1953393 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5956. Min Range: -6.5956
Max Act: 6.2519. Min Act: -0.1700
Data Index: 5954376 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19