Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2169 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.7776. Min Act: -0.1700
Data Index: 195618 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.6214. Min Act: -0.1700
Data Index: 8687216 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.5589. Min Act: -0.1700
Data Index: 536877 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.4026. Min Act: -0.1700
Data Index: 6279199 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.3401. Min Act: -0.1700
Data Index: 1218005 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.2776. Min Act: -0.1700
Data Index: 6208021 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.2151. Min Act: -0.1700
Data Index: 6001661 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.2151. Min Act: -0.1700
Data Index: 4948259 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.2151. Min Act: -0.1700
Data Index: 3458017 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.2151. Min Act: -0.1700
Data Index: 4896757 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.2151. Min Act: -0.1700
Data Index: 8057898 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1526. Min Act: -0.1700
Data Index: 8137344 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1839. Min Act: -0.1700
Data Index: 1616487 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1839. Min Act: -0.1700
Data Index: 8606339 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1526. Min Act: -0.1700
Data Index: 3768604 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1526. Min Act: -0.1700
Data Index: 8812244 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1526. Min Act: -0.1700
Data Index: 8380098 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1526. Min Act: -0.1700
Data Index: 6223185 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1526. Min Act: -0.1700
Data Index: 4462903 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7776. Min Range: -5.7776
Max Act: 5.1214. Min Act: -0.1700
Data Index: 2440560 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19