Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4385 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.6020. Min Act: -0.1700
Data Index: 544184 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3827. Min Act: -0.1700
Data Index: 741274 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3513. Min Act: -0.1700
Data Index: 5922740 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3200. Min Act: -0.1700
Data Index: 3220706 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3043. Min Act: -0.1700
Data Index: 8164825 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3043. Min Act: -0.1700
Data Index: 2085882 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3043. Min Act: -0.1700
Data Index: 287160 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2886. Min Act: -0.1700
Data Index: 335473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2886. Min Act: -0.1700
Data Index: 8185154 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.3043. Min Act: -0.1700
Data Index: 2259358 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2572. Min Act: -0.1700
Data Index: 4228212 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2572. Min Act: -0.1700
Data Index: 978241 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2572. Min Act: -0.1700
Data Index: 2346293 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2414. Min Act: -0.1700
Data Index: 3003041 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2414. Min Act: -0.1700
Data Index: 5408712 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2257. Min Act: -0.1700
Data Index: 8546010 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2257. Min Act: -0.1700
Data Index: 6457058 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2257. Min Act: -0.1700
Data Index: 3624975 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2100. Min Act: -0.1700
Data Index: 2325129 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6020. Min Range: -3.6020
Max Act: 3.2100. Min Act: -0.1700
Data Index: 2073382 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19