Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5809 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.6269. Min Act: -0.1700
Data Index: 1104630 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.4394. Min Act: -0.1700
Data Index: 2550964 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.3769. Min Act: -0.1700
Data Index: 238792 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.4081. Min Act: -0.1700
Data Index: 3185330 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.3769. Min Act: -0.1700
Data Index: 2418084 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.3769. Min Act: -0.1700
Data Index: 2665862 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.3456. Min Act: -0.1700
Data Index: 5605169 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.3456. Min Act: -0.1700
Data Index: 5597153 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.3144. Min Act: -0.1700
Data Index: 182732 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2831. Min Act: -0.1700
Data Index: 5124149 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2831. Min Act: -0.1700
Data Index: 1789136 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2519. Min Act: -0.1700
Data Index: 6213193 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2519. Min Act: -0.1700
Data Index: 2553717 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2519. Min Act: -0.1700
Data Index: 3609674 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2519. Min Act: -0.1700
Data Index: 154381 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2206. Min Act: -0.1700
Data Index: 6521633 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2206. Min Act: -0.1700
Data Index: 3776857 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2206. Min Act: -0.1700
Data Index: 5227350 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.2206. Min Act: -0.1700
Data Index: 4017488 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6269. Min Range: -5.6269
Max Act: 5.1894. Min Act: -0.1700
Data Index: 3900224 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19