Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.5131. Min Act: -0.1700
Data Index: 6216013 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.4194. Min Act: -0.1700
Data Index: 1162160 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.3881. Min Act: -0.1700
Data Index: 3431478 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.3569. Min Act: -0.1700
Data Index: 8041690 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.3256. Min Act: -0.1700
Data Index: 906649 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.3256. Min Act: -0.1700
Data Index: 6671157 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.3256. Min Act: -0.1700
Data Index: 158878 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2944. Min Act: -0.1700
Data Index: 3698956 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4265317 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 7797394 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 4747091 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 3252774 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 4426623 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 8781466 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 2842300 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1697
Data Index: 7467291 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 7123080 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 6497194 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2631. Min Act: -0.1700
Data Index: 1642277 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5131. Min Range: -5.5131
Max Act: 5.2319. Min Act: -0.1700
Data Index: 4923016 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19