Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2176 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 2686324 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 7246693 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6208. Min Act: -0.1700
Data Index: 4953721 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5270. Min Act: -0.1700
Data Index: 4443954 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 7584934 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 2443885 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 3446904 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 7393193 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4020. Min Act: -0.1700
Data Index: 1918397 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 4401662 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 8485411 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 2480173 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3083. Min Act: -0.1700
Data Index: 8303289 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2770. Min Act: -0.1700
Data Index: 6371476 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2770. Min Act: -0.1700
Data Index: 3697573 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2770. Min Act: -0.1700
Data Index: 3364536 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2458. Min Act: -0.1700
Data Index: 1194163 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6281656 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6285756 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2458. Min Act: -0.1700
Data Index: 382014 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19