Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.7370. Min Act: -0.1700
Data Index: 4765262 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.3933. Min Act: -0.1700
Data Index: 525809 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.3933. Min Act: -0.1700
Data Index: 541280 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.3620. Min Act: -0.1700
Data Index: 7843347 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.3307. Min Act: -0.1700
Data Index: 8125094 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.3307. Min Act: -0.1700
Data Index: 6700731 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2995. Min Act: -0.1700
Data Index: 1749180 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2995. Min Act: -0.1700
Data Index: 3707259 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2995. Min Act: -0.1700
Data Index: 2067081 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2995. Min Act: -0.1700
Data Index: 6712632 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2995. Min Act: -0.1700
Data Index: 5036725 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2682. Min Act: -0.1700
Data Index: 3072114 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2682. Min Act: -0.1700
Data Index: 1193148 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2682. Min Act: -0.1700
Data Index: 261315 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2057. Min Act: -0.1700
Data Index: 1106935 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2370. Min Act: -0.1700
Data Index: 4981941 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2370. Min Act: -0.1700
Data Index: 2592134 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2370. Min Act: -0.1700
Data Index: 1889812 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2370. Min Act: -0.1700
Data Index: 133818 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7370. Min Range: -4.7370
Max Act: 4.2370. Min Act: -0.1700
Data Index: 5545548 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19