Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0437. Min Range: -6.0437
Max Act: 6.0437. Min Act: -0.1700
Data Index: 4097587 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.7624. Min Act: -0.1700
Data Index: 1486285 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.7312. Min Act: -0.1700
Data Index: 7300416 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.7312. Min Act: -0.1700
Data Index: 6842632 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.6687. Min Act: -0.1700
Data Index: 218191 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.6062. Min Act: -0.1700
Data Index: 301258 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5437. Min Act: -0.1700
Data Index: 1619116 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5749. Min Act: -0.1700
Data Index: 3609578 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5749. Min Act: -0.1700
Data Index: 2278309 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5749. Min Act: -0.1700
Data Index: 8627280 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5437. Min Act: -0.1700
Data Index: 3384948 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5749. Min Act: -0.1700
Data Index: 7338051 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5124. Min Act: -0.1700
Data Index: 5008260 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5124. Min Act: -0.1700
Data Index: 5727063 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5124. Min Act: -0.1700
Data Index: 8346362 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.5124. Min Act: -0.1700
Data Index: 4182671 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 8091875 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 2865872 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 302744 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0437. Min Range: -6.0437
Max Act: 5.4812. Min Act: -0.1700
Data Index: 1041046 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19