Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6120 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3140. Min Range: -8.3140
Max Act: 8.3140. Min Act: -0.1700
Data Index: 3986339 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3140. Min Range: -8.3140
Max Act: 8.1890. Min Act: -0.1700
Data Index: 1261015 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3140. Min Range: -8.3140
Max Act: 8.1265. Min Act: -0.1700
Data Index: 8295866 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3140. Min Range: -8.3140
Max Act: 8.0640. Min Act: -0.1700
Data Index: 3411790 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3140. Min Range: -8.3140
Max Act: 8.0015. Min Act: -0.1700
Data Index: 252593 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.9078. Min Act: -0.1700
Data Index: 4291843 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.8140. Min Act: -0.1700
Data Index: 3881570 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.7515. Min Act: -0.1700
Data Index: 6750178 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.7203. Min Act: -0.1700
Data Index: 892295 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.6890. Min Act: -0.1700
Data Index: 2071713 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.6890. Min Act: -0.1700
Data Index: 2071711 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5953. Min Act: -0.1700
Data Index: 3870767 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5953. Min Act: -0.1700
Data Index: 7168154 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5640. Min Act: -0.1700
Data Index: 1618545 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5328. Min Act: -0.1700
Data Index: 4518158 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5328. Min Act: -0.1700
Data Index: 1618544 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5015. Min Act: -0.1700
Data Index: 864931 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.5015. Min Act: -0.1700
Data Index: 4382424 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.4703. Min Act: -0.1700
Data Index: 637548 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3140. Min Range: -8.3140
Max Act: 7.4390. Min Act: -0.1700
Data Index: 7485434 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19