Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1974 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 3529324 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.7893. Min Act: -0.1700
Data Index: 536451 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.4768. Min Act: -0.1700
Data Index: 7267655 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.5081. Min Act: -0.1700
Data Index: 3560350 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.4456. Min Act: -0.1700
Data Index: 1209565 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.4456. Min Act: -0.1700
Data Index: 554546 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3206. Min Act: -0.1700
Data Index: 7602000 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3206. Min Act: -0.1700
Data Index: 6959817 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 5505490 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 5481515 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3206. Min Act: -0.1700
Data Index: 2986424 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3206. Min Act: -0.1700
Data Index: 2524433 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3206. Min Act: -0.1700
Data Index: 6881287 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.2581. Min Act: -0.1700
Data Index: 402734 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.3206. Min Act: -0.1700
Data Index: 2407436 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.2893. Min Act: -0.1700
Data Index: 4818833 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.2268. Min Act: -0.1700
Data Index: 2690991 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.2268. Min Act: -0.1700
Data Index: 266392 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.2268. Min Act: -0.1700
Data Index: 877282 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9143. Min Range: -5.9143
Max Act: 5.1643. Min Act: -0.1700
Data Index: 7492489 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19