Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5785 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4932. Min Range: -8.4932
Max Act: 8.4932. Min Act: -0.1700
Data Index: 7362857 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.8057. Min Act: -0.1700
Data Index: 6185209 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.6807. Min Act: -0.1700
Data Index: 8356978 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.6182. Min Act: -0.1700
Data Index: 2405586 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.6182. Min Act: -0.1700
Data Index: 3112483 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.4932. Min Act: -0.1700
Data Index: 3264793 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.5244. Min Act: -0.1700
Data Index: 5187758 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.3369. Min Act: -0.1700
Data Index: 4839722 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.3369. Min Act: -0.1700
Data Index: 7504020 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.3369. Min Act: -0.1700
Data Index: 2934037 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.3369. Min Act: -0.1700
Data Index: 6948219 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.3057. Min Act: -0.1700
Data Index: 1598088 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.2432. Min Act: -0.1700
Data Index: 7353624 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.2119. Min Act: -0.1700
Data Index: 2315945 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.1807. Min Act: -0.1700
Data Index: 4762726 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.1494. Min Act: -0.1700
Data Index: 2445968 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.1182. Min Act: -0.1700
Data Index: 5127180 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.1182. Min Act: -0.1700
Data Index: 7561798 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.0244. Min Act: -0.1700
Data Index: 6826211 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4932. Min Range: -8.4932
Max Act: 7.0244. Min Act: -0.1700
Data Index: 7658947 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19