Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.3960. Min Act: -0.1700
Data Index: 8799066 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.3022. Min Act: -0.1700
Data Index: 6231387 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.2397. Min Act: -0.1700
Data Index: 15592 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.2397. Min Act: -0.1700
Data Index: 4813147 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.1460. Min Act: -0.1700
Data Index: 2356195 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.0835. Min Act: -0.1700
Data Index: 4759458 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.1147. Min Act: -0.1700
Data Index: 6857277 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.0835. Min Act: -0.1700
Data Index: 2442732 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.0210. Min Act: -0.1700
Data Index: 5627413 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.0522. Min Act: -0.1700
Data Index: 2138250 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3960. Min Range: -6.3960
Max Act: 6.0210. Min Act: -0.1700
Data Index: 3217968 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9897. Min Act: -0.1700
Data Index: 5305268 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9897. Min Act: -0.1700
Data Index: 5348136 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9585. Min Act: -0.1700
Data Index: 119526 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9585. Min Act: -0.1700
Data Index: 140489 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9585. Min Act: -0.1700
Data Index: 8721943 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9272. Min Act: -0.1700
Data Index: 3476510 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9272. Min Act: -0.1700
Data Index: 8730209 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.9272. Min Act: -0.1700
Data Index: 2701158 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3960. Min Range: -6.3960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 935205 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19