Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1114. Min Range: -7.1114
Max Act: 7.1114. Min Act: -0.1700
Data Index: 1548651 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1114. Min Range: -7.1114
Max Act: 7.0489. Min Act: -0.1700
Data Index: 7904586 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1114. Min Range: -7.1114
Max Act: 7.0489. Min Act: -0.1700
Data Index: 5214123 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.8927. Min Act: -0.1700
Data Index: 4696433 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.7989. Min Act: -0.1700
Data Index: 3590433 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.7677. Min Act: -0.1700
Data Index: 1769700 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.7677. Min Act: -0.1700
Data Index: 2861099 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.7677. Min Act: -0.1700
Data Index: 5946679 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.7364. Min Act: -0.1700
Data Index: 7641342 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.7052. Min Act: -0.1700
Data Index: 4676138 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.6114. Min Act: -0.1700
Data Index: 6408235 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.6114. Min Act: -0.1700
Data Index: 1355177 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.5802. Min Act: -0.1700
Data Index: 1280376 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.5802. Min Act: -0.1700
Data Index: 1805934 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.5177. Min Act: -0.1700
Data Index: 8285876 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.5177. Min Act: -0.1700
Data Index: 5790261 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.5177. Min Act: -0.1700
Data Index: 4149159 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.5177. Min Act: -0.1700
Data Index: 2548810 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.4864. Min Act: -0.1700
Data Index: 6308710 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1114. Min Range: -7.1114
Max Act: 6.4864. Min Act: -0.1700
Data Index: 7969287 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19