Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1005. Min Range: -7.1005
Max Act: 7.1005. Min Act: -0.1700
Data Index: 1150826 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1005. Min Range: -7.1005
Max Act: 7.0380. Min Act: -0.1700
Data Index: 1382887 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.9443. Min Act: -0.1700
Data Index: 3583620 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.9130. Min Act: -0.1700
Data Index: 727568 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8505. Min Act: -0.1700
Data Index: 507277 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8505. Min Act: -0.1700
Data Index: 4301070 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8818. Min Act: -0.1700
Data Index: 6320534 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8818. Min Act: -0.1700
Data Index: 4606517 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8505. Min Act: -0.1700
Data Index: 7761204 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8193. Min Act: -0.1700
Data Index: 8740487 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8193. Min Act: -0.1700
Data Index: 6356628 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.7568. Min Act: -0.1700
Data Index: 2215807 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8193. Min Act: -0.1700
Data Index: 4352744 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.7880. Min Act: -0.1700
Data Index: 2004425 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8505. Min Act: -0.1700
Data Index: 6946007 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.7880. Min Act: -0.1700
Data Index: 3200747 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.7880. Min Act: -0.1700
Data Index: 4775310 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.7568. Min Act: -0.1700
Data Index: 5808368 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8193. Min Act: -0.1700
Data Index: 8692723 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1005. Min Range: -7.1005
Max Act: 6.8193. Min Act: -0.1700
Data Index: 3805246 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19