Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.8767. Min Act: -0.1700
Data Index: 8007231 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.9080. Min Act: -0.1700
Data Index: 4146361 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.9080. Min Act: -0.1700
Data Index: 723968 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.8455. Min Act: -0.1700
Data Index: 2258710 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.8455. Min Act: -0.1700
Data Index: 4217364 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.7517. Min Act: -0.1700
Data Index: 384108 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.6892. Min Act: -0.1700
Data Index: 703124 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.6892. Min Act: -0.1700
Data Index: 188815 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.6580. Min Act: -0.1700
Data Index: 4278905 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.6267. Min Act: -0.1700
Data Index: 693713 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.6267. Min Act: -0.1700
Data Index: 2348707 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5955. Min Act: -0.1700
Data Index: 212670 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5955. Min Act: -0.1700
Data Index: 4242050 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5955. Min Act: -0.1700
Data Index: 3852476 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5955. Min Act: -0.1700
Data Index: 3111 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5642. Min Act: -0.1700
Data Index: 4371396 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5642. Min Act: -0.1700
Data Index: 5508737 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5330. Min Act: -0.1700
Data Index: 3429213 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5330. Min Act: -0.1700
Data Index: 2686749 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9080. Min Range: -4.9080
Max Act: 4.5330. Min Act: -0.1700
Data Index: 1879686 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19