Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.9864. Min Act: -0.1700
Data Index: 3561718 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.8302. Min Act: -0.1700
Data Index: 7653618 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.7052. Min Act: -0.1700
Data Index: 7875904 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6739. Min Act: -0.1700
Data Index: 4789352 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6739. Min Act: -0.1700
Data Index: 7470987 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6739. Min Act: -0.1700
Data Index: 2759735 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6427. Min Act: -0.1700
Data Index: 4998386 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1635105 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6114. Min Act: -0.1700
Data Index: 7099375 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6114. Min Act: -0.1700
Data Index: 5569308 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.5802. Min Act: -0.1700
Data Index: 3336017 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.6114. Min Act: -0.1700
Data Index: 281674 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.5489. Min Act: -0.1700
Data Index: 1449501 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.5802. Min Act: -0.1700
Data Index: 6707159 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.5489. Min Act: -0.1700
Data Index: 6022037 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.5177. Min Act: -0.1700
Data Index: 6410488 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.5177. Min Act: -0.1700
Data Index: 1593307 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.4864. Min Act: -0.1700
Data Index: 5864178 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.4864. Min Act: -0.1700
Data Index: 843643 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9864. Min Range: -5.9864
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4590366 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19