Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5191 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0136. Min Range: -6.0136
Max Act: 6.0136. Min Act: -0.1700
Data Index: 5635356 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.9824. Min Act: -0.1700
Data Index: 7385341 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8574. Min Act: -0.1700
Data Index: 4661036 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7949. Min Act: -0.1700
Data Index: 1712767 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7087059 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8261. Min Act: -0.1700
Data Index: 23232 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 4374749 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 2439675 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7324. Min Act: -0.1700
Data Index: 6727478 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7324. Min Act: -0.1700
Data Index: 2821613 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 7650004 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7324. Min Act: -0.1700
Data Index: 3181397 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7011. Min Act: -0.1700
Data Index: 1799639 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7011. Min Act: -0.1700
Data Index: 6052805 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7011. Min Act: -0.1700
Data Index: 8294950 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7011. Min Act: -0.1700
Data Index: 2941395 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.6699. Min Act: -0.1700
Data Index: 8008720 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.6699. Min Act: -0.1700
Data Index: 6061977 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.6699. Min Act: -0.1700
Data Index: 1305830 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.6699. Min Act: -0.1700
Data Index: 8024689 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19