Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.7585. Min Act: -0.1700
Data Index: 7163464 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.6022. Min Act: -0.1700
Data Index: 7812710 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.5397. Min Act: -0.1700
Data Index: 1302097 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.4460. Min Act: -0.1700
Data Index: 7046 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.4147. Min Act: -0.1700
Data Index: 7763022 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.3835. Min Act: -0.1700
Data Index: 6861661 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.3522. Min Act: -0.1700
Data Index: 8239347 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.3522. Min Act: -0.1700
Data Index: 5283996 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.3210. Min Act: -0.1700
Data Index: 647120 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2897. Min Act: -0.1700
Data Index: 6832658 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2897. Min Act: -0.1700
Data Index: 4374024 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2585. Min Act: -0.1700
Data Index: 3665252 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2272. Min Act: -0.1700
Data Index: 8388838 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2272. Min Act: -0.1700
Data Index: 8546611 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2272. Min Act: -0.1700
Data Index: 5723465 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.1960. Min Act: -0.1700
Data Index: 7730143 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.2272. Min Act: -0.1700
Data Index: 1698700 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.1960. Min Act: -0.1700
Data Index: 2429806 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.1335. Min Act: -0.1700
Data Index: 8280164 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7585. Min Range: -6.7585
Max Act: 6.1647. Min Act: -0.1700
Data Index: 7805468 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19