Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1658. Min Act: -0.1700
Data Index: 8481432 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1343. Min Act: -0.1700
Data Index: 6019627 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1343. Min Act: -0.1700
Data Index: 8309882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1186. Min Act: -0.1700
Data Index: 7115339 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1186. Min Act: -0.1700
Data Index: 3440997 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1028. Min Act: -0.1700
Data Index: 31904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1028. Min Act: -0.1700
Data Index: 5546039 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.1028. Min Act: -0.1700
Data Index: 6796285 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0870. Min Act: -0.1700
Data Index: 1306366 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0870. Min Act: -0.1700
Data Index: 7939242 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0870. Min Act: -0.1700
Data Index: 6258640 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0870. Min Act: -0.1700
Data Index: 322926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0870. Min Act: -0.1700
Data Index: 7160630 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0713. Min Act: -0.1700
Data Index: 2915355 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 4438250 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 3712340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0555. Min Act: -0.1700
Data Index: 737787 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0397. Min Act: -0.1700
Data Index: 3184763 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0397. Min Act: -0.1700
Data Index: 5289118 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1658. Min Range: -3.1658
Max Act: 3.0397. Min Act: -0.1700
Data Index: 2837629 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19