Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6208 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.7224. Min Act: -0.1697
Data Index: 8466685 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.6912. Min Act: -0.1700
Data Index: 7402489 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5974. Min Act: -0.1700
Data Index: 4556472 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.6287. Min Act: -0.1693
Data Index: 5751346 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.6287. Min Act: -0.1700
Data Index: 7365992 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5974. Min Act: -0.1700
Data Index: 4323929 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5974. Min Act: -0.1700
Data Index: 7920779 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5974. Min Act: -0.1700
Data Index: 3006542 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5974. Min Act: -0.1695
Data Index: 1664260 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5662. Min Act: -0.1700
Data Index: 7283896 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5662. Min Act: -0.1700
Data Index: 4671585 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5662. Min Act: -0.1700
Data Index: 3453271 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5662. Min Act: -0.1700
Data Index: 6305208 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5037. Min Act: -0.1700
Data Index: 3625259 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5037. Min Act: -0.1700
Data Index: 1388167 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5037. Min Act: -0.1700
Data Index: 3998755 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5037. Min Act: -0.1700
Data Index: 190419 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.4724. Min Act: -0.1700
Data Index: 5565181 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5037. Min Act: -0.1698
Data Index: 3807992 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5037. Min Act: -0.1700
Data Index: 3178537 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19