Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.6115. Min Act: -0.1700
Data Index: 5213347 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.4240. Min Act: -0.1700
Data Index: 5401345 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.3615. Min Act: -0.1700
Data Index: 1005732 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.2990. Min Act: -0.1700
Data Index: 3813501 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.2990. Min Act: -0.1700
Data Index: 2589295 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.2365. Min Act: -0.1700
Data Index: 6400916 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.2365. Min Act: -0.1700
Data Index: 8023095 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.1740. Min Act: -0.1700
Data Index: 1927660 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.1115. Min Act: -0.1700
Data Index: 4147575 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.1740. Min Act: -0.1700
Data Index: 5742549 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.1740. Min Act: -0.1700
Data Index: 3409289 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6115. Min Range: -8.6115
Max Act: 8.1115. Min Act: -0.1700
Data Index: 6544415 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9865. Min Act: -0.1700
Data Index: 2829527 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9865. Min Act: -0.1700
Data Index: 4745184 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9865. Min Act: -0.1700
Data Index: 1643410 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9865. Min Act: -0.1700
Data Index: 2265293 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9240. Min Act: -0.1700
Data Index: 5602874 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9240. Min Act: -0.1700
Data Index: 6532422 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.9552. Min Act: -0.1700
Data Index: 2560985 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6115. Min Range: -8.6115
Max Act: 7.8927. Min Act: -0.1700
Data Index: 3148415 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19