Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4576 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0137. Min Range: -3.0137
Max Act: 3.0137. Min Act: -0.1700
Data Index: 4151578 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.9188. Min Act: -0.1700
Data Index: 8744238 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8712. Min Act: -0.1700
Data Index: 3072703 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8871. Min Act: -0.1700
Data Index: 7571877 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8394. Min Act: -0.1700
Data Index: 2991520 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8394. Min Act: -0.1700
Data Index: 5871433 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8235. Min Act: -0.1700
Data Index: 5147886 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8076. Min Act: -0.1700
Data Index: 6063071 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.8076. Min Act: -0.1700
Data Index: 1628012 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7917. Min Act: -0.1700
Data Index: 3408853 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7917. Min Act: -0.1700
Data Index: 6179279 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7917. Min Act: -0.1700
Data Index: 967519 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7917. Min Act: -0.1700
Data Index: 1146844 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7758. Min Act: -0.1700
Data Index: 431959 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7917. Min Act: -0.1700
Data Index: 6045176 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7758. Min Act: -0.1700
Data Index: 8820248 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7758. Min Act: -0.1700
Data Index: 3930502 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7758. Min Act: -0.1700
Data Index: 6871616 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7758. Min Act: -0.1700
Data Index: 3899292 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0137. Min Range: -3.0137
Max Act: 2.7598. Min Act: -0.1700
Data Index: 4692121 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19