Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.3177. Min Act: -0.1700
Data Index: 1022279 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.2706. Min Act: -0.1700
Data Index: 5909447 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.1133. Min Act: -0.1700
Data Index: 3744138 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.1133. Min Act: -0.1700
Data Index: 7324117 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.1133. Min Act: -0.1700
Data Index: 5020789 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0975. Min Act: -0.1700
Data Index: 2057925 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0818. Min Act: -0.1700
Data Index: 5607201 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0818. Min Act: -0.1700
Data Index: 1417319 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0344. Min Act: -0.1700
Data Index: 586432 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0502. Min Act: -0.1700
Data Index: 7864235 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0187. Min Act: -0.1700
Data Index: 6790998 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9871. Min Act: -0.1700
Data Index: 8585367 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3177. Min Range: -3.3177
Max Act: 3.0344. Min Act: -0.1700
Data Index: 536115 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9871. Min Act: -0.1700
Data Index: 7105422 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9871. Min Act: -0.1700
Data Index: 5293000 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9712. Min Act: -0.1700
Data Index: 7646493 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9871. Min Act: -0.1700
Data Index: 2632065 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9712. Min Act: -0.1700
Data Index: 2200257 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9712. Min Act: -0.1699
Data Index: 7969505 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3177. Min Range: -3.3177
Max Act: 2.9396. Min Act: -0.1700
Data Index: 7246158 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19