Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3111 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0290. Min Range: -6.0290
Max Act: 6.0290. Min Act: -0.1700
Data Index: 110861 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.9977. Min Act: -0.1700
Data Index: 618253 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.9040. Min Act: -0.1700
Data Index: 4289447 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.8415. Min Act: -0.1700
Data Index: 8009679 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.8102. Min Act: -0.1700
Data Index: 5147413 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 4395350 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 3168041 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 7756235 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 6188683 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 1220532 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.8102. Min Act: -0.1700
Data Index: 8466513 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7477. Min Act: -0.1700
Data Index: 6244480 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 1759383 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 6003741 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7477. Min Act: -0.1700
Data Index: 7095992 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7477. Min Act: -0.1700
Data Index: 7360512 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7477. Min Act: -0.1700
Data Index: 4473159 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7477. Min Act: -0.1700
Data Index: 5494683 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7790. Min Act: -0.1700
Data Index: 210783 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0290. Min Range: -6.0290
Max Act: 5.7165. Min Act: -0.1700
Data Index: 6188863 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19