Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.1580. Min Act: -0.1700
Data Index: 5560092 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.1580. Min Act: -0.1700
Data Index: 2487960 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.1267. Min Act: -0.1700
Data Index: 4333957 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.1267. Min Act: -0.1700
Data Index: 6327780 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.1267. Min Act: -0.1700
Data Index: 1098071 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0955. Min Act: -0.1700
Data Index: 778248 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0955. Min Act: -0.1700
Data Index: 6278975 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0330. Min Act: -0.1700
Data Index: 195870 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0330. Min Act: -0.1700
Data Index: 8311303 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0330. Min Act: -0.1700
Data Index: 8709307 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1580. Min Range: -5.1580
Max Act: 4.9705. Min Act: -0.1700
Data Index: 7337401 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4586019 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0017. Min Act: -0.1700
Data Index: 3428847 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0017. Min Act: -0.1700
Data Index: 5537189 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0017. Min Act: -0.1700
Data Index: 7165350 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1580. Min Range: -5.1580
Max Act: 5.0017. Min Act: -0.1700
Data Index: 5564403 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1580. Min Range: -5.1580
Max Act: 4.9705. Min Act: -0.1700
Data Index: 4247146 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1580. Min Range: -5.1580
Max Act: 4.9705. Min Act: -0.1700
Data Index: 6173213 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1580. Min Range: -5.1580
Max Act: 4.9392. Min Act: -0.1700
Data Index: 3423586 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1580. Min Range: -5.1580
Max Act: 4.9392. Min Act: -0.1700
Data Index: 945754 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19