Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4761 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4885. Min Range: -6.4885
Max Act: 6.4885. Min Act: -0.1700
Data Index: 5067883 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4885. Min Range: -6.4885
Max Act: 6.2073. Min Act: -0.1700
Data Index: 5796138 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4885. Min Range: -6.4885
Max Act: 6.1135. Min Act: -0.1700
Data Index: 7011111 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4885. Min Range: -6.4885
Max Act: 6.0198. Min Act: -0.1700
Data Index: 4379248 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4885. Min Range: -6.4885
Max Act: 6.0198. Min Act: -0.1700
Data Index: 1432363 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.9260. Min Act: -0.1700
Data Index: 8565532 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8635. Min Act: -0.1700
Data Index: 1236245 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8635. Min Act: -0.1700
Data Index: 4156578 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8635. Min Act: -0.1700
Data Index: 2702189 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8323. Min Act: -0.1700
Data Index: 2461090 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8323. Min Act: -0.1700
Data Index: 4782766 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8010. Min Act: -0.1700
Data Index: 8391983 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8010. Min Act: -0.1700
Data Index: 6088385 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.7698. Min Act: -0.1700
Data Index: 6211318 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8010. Min Act: -0.1700
Data Index: 474084 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.8010. Min Act: -0.1700
Data Index: 5453137 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.7698. Min Act: -0.1700
Data Index: 3945965 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.7698. Min Act: -0.1700
Data Index: 2330708 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.7385. Min Act: -0.1700
Data Index: 5700815 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4885. Min Range: -6.4885
Max Act: 5.7073. Min Act: -0.1700
Data Index: 5711480 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19