Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.4521. Min Act: -0.1700
Data Index: 6836457 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.4208. Min Act: -0.1700
Data Index: 2631944 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.4208. Min Act: -0.1700
Data Index: 4008908 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.3583. Min Act: -0.1700
Data Index: 7877590 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.3896. Min Act: -0.1700
Data Index: 4008901 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.3583. Min Act: -0.1700
Data Index: 2565128 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.3271. Min Act: -0.1700
Data Index: 187942 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2958. Min Act: -0.1700
Data Index: 2348610 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2958. Min Act: -0.1700
Data Index: 2168015 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.3271. Min Act: -0.1700
Data Index: 1289839 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2958. Min Act: -0.1700
Data Index: 4008909 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 4008902 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 3136734 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 1413937 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 4042191 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2333. Min Act: -0.1700
Data Index: 4008900 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2333. Min Act: -0.1700
Data Index: 5484020 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2333. Min Act: -0.1700
Data Index: 844280 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2333. Min Act: -0.1700
Data Index: 7478838 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2333. Min Act: -0.1700
Data Index: 2565136 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19