Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.9574. Min Act: -0.1700
Data Index: 2720598 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.9887. Min Act: -0.1700
Data Index: 7019845 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.9574. Min Act: -0.1700
Data Index: 5212884 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.9262. Min Act: -0.1700
Data Index: 256144 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8949. Min Act: -0.1700
Data Index: 2069350 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8949. Min Act: -0.1700
Data Index: 8699025 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8949. Min Act: -0.1700
Data Index: 390854 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8637. Min Act: -0.1700
Data Index: 3278590 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8637. Min Act: -0.1700
Data Index: 6606455 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8637. Min Act: -0.1700
Data Index: 6799884 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8637. Min Act: -0.1700
Data Index: 3070248 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8637. Min Act: -0.1700
Data Index: 1717324 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8637. Min Act: -0.1700
Data Index: 1173719 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 5804042 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 460613 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 2771269 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 1457854 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 2237680 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 5031812 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9887. Min Range: -4.9887
Max Act: 4.8324. Min Act: -0.1700
Data Index: 2234519 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19