Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5091 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1445. Min Range: -5.1445
Max Act: 5.1445. Min Act: -0.1700
Data Index: 3206983 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1445. Min Range: -5.1445
Max Act: 5.0195. Min Act: -0.1700
Data Index: 3295966 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1445. Min Range: -5.1445
Max Act: 5.0507. Min Act: -0.1699
Data Index: 2510596 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7768946 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.9570. Min Act: -0.1700
Data Index: 6080117 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7570490 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8945. Min Act: -0.1700
Data Index: 8417948 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.9257. Min Act: -0.1700
Data Index: 4156714 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.9257. Min Act: -0.1700
Data Index: 6658477 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8945. Min Act: -0.1700
Data Index: 152478 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8945. Min Act: -0.1697
Data Index: 7473449 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8945. Min Act: -0.1700
Data Index: 2423421 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8945. Min Act: -0.1700
Data Index: 6891784 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8945. Min Act: -0.1700
Data Index: 3108408 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8632. Min Act: -0.1699
Data Index: 3347466 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8320. Min Act: -0.1700
Data Index: 2021526 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8632. Min Act: -0.1699
Data Index: 968188 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8632. Min Act: -0.1700
Data Index: 264562 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8007. Min Act: -0.1700
Data Index: 4156710 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1445. Min Range: -5.1445
Max Act: 4.8007. Min Act: -0.1700
Data Index: 944797 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19