Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.6182. Min Act: -0.1700
Data Index: 8204519 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.3682. Min Act: -0.1700
Data Index: 2004176 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4372442 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.3057. Min Act: -0.1700
Data Index: 450989 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4106096 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.3369. Min Act: -0.1700
Data Index: 7383980 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2744. Min Act: -0.1700
Data Index: 6059524 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1700
Data Index: 5701044 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1700
Data Index: 5350717 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1700
Data Index: 2235052 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1700
Data Index: 789345 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1699
Data Index: 8736613 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1700
Data Index: 3720266 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2432. Min Act: -0.1700
Data Index: 3642421 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2119. Min Act: -0.1700
Data Index: 3312461 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2119. Min Act: -0.1700
Data Index: 7640362 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2119. Min Act: -0.1700
Data Index: 6473018 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2119. Min Act: -0.1700
Data Index: 7565701 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.1807. Min Act: -0.1700
Data Index: 4095188 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6182. Min Range: -5.6182
Max Act: 5.2119. Min Act: -0.1700
Data Index: 5060796 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19