Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.4400. Min Act: -0.1700
Data Index: 2435344 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.1587. Min Act: -0.1700
Data Index: 5773105 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.1275. Min Act: -0.1700
Data Index: 6144263 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0025. Min Act: -0.1700
Data Index: 3013043 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0025. Min Act: -0.1700
Data Index: 6286674 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.9712. Min Act: -0.1700
Data Index: 8675912 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.9400. Min Act: -0.1700
Data Index: 6032832 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.9087. Min Act: -0.1700
Data Index: 8070513 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8775. Min Act: -0.1700
Data Index: 4537915 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8462. Min Act: -0.1700
Data Index: 7582356 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8462. Min Act: -0.1700
Data Index: 5634216 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8462. Min Act: -0.1700
Data Index: 7073151 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7837. Min Act: -0.1700
Data Index: 6244038 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7525. Min Act: -0.1700
Data Index: 2688359 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7525. Min Act: -0.1700
Data Index: 5330908 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7525. Min Act: -0.1700
Data Index: 7239371 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7212. Min Act: -0.1700
Data Index: 6373276 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7212. Min Act: -0.1700
Data Index: 8632202 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.6900. Min Act: -0.1700
Data Index: 5210317 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.6900. Min Act: -0.1700
Data Index: 4834440 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19