Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3669 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.6173. Min Act: -0.1700
Data Index: 1954477 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.4298. Min Act: -0.1700
Data Index: 4939509 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.3985. Min Act: -0.1700
Data Index: 5077524 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.3985. Min Act: -0.1700
Data Index: 8068211 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.3048. Min Act: -0.1700
Data Index: 162831 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2423. Min Act: -0.1700
Data Index: 7956860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2735. Min Act: -0.1700
Data Index: 2908460 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2735. Min Act: -0.1700
Data Index: 5780696 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2423. Min Act: -0.1700
Data Index: 5784698 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2423. Min Act: -0.1700
Data Index: 6509116 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2110. Min Act: -0.1700
Data Index: 2289122 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.1798. Min Act: -0.1700
Data Index: 610627 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2110. Min Act: -0.1700
Data Index: 41939 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2110. Min Act: -0.1700
Data Index: 6676936 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.1485. Min Act: -0.1700
Data Index: 2973139 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.1485. Min Act: -0.1700
Data Index: 7281096 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.1485. Min Act: -0.1700
Data Index: 71977 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2110. Min Act: -0.1700
Data Index: 2269336 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.2110. Min Act: -0.1700
Data Index: 1201476 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6173. Min Range: -5.6173
Max Act: 5.1485. Min Act: -0.1700
Data Index: 4862881 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19