Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7582. Min Range: -8.7582
Max Act: 8.7582. Min Act: -0.1700
Data Index: 5401265 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7582. Min Range: -8.7582
Max Act: 8.4457. Min Act: -0.1700
Data Index: 5252512 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7582. Min Range: -8.7582
Max Act: 8.1957. Min Act: -0.1700
Data Index: 4679257 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7582. Min Range: -8.7582
Max Act: 8.1957. Min Act: -0.1700
Data Index: 5395953 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7582. Min Range: -8.7582
Max Act: 8.0707. Min Act: -0.1700
Data Index: 6266146 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.9457. Min Act: -0.1700
Data Index: 5252511 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.8207. Min Act: -0.1700
Data Index: 7382086 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 7214020 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.7895. Min Act: -0.1700
Data Index: 5425811 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.7270. Min Act: -0.1700
Data Index: 7141932 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.7270. Min Act: -0.1700
Data Index: 6266164 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.7270. Min Act: -0.1700
Data Index: 5105833 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6957. Min Act: -0.1700
Data Index: 1177324 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6957. Min Act: -0.1700
Data Index: 7141940 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6645. Min Act: -0.1700
Data Index: 3530080 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6332. Min Act: -0.1700
Data Index: 3809245 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6020. Min Act: -0.1700
Data Index: 6004279 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6020. Min Act: -0.1700
Data Index: 2146103 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6332. Min Act: -0.1700
Data Index: 5342154 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7582. Min Range: -8.7582
Max Act: 7.6020. Min Act: -0.1700
Data Index: 67862 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19