Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0920. Min Range: -4.0920
Max Act: 4.0920. Min Act: -0.1700
Data Index: 3401808 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0920. Min Range: -4.0920
Max Act: 4.0294. Min Act: -0.1700
Data Index: 4991167 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.9982. Min Act: -0.1700
Data Index: 4455438 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.9669. Min Act: -0.1700
Data Index: 7434477 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.9357. Min Act: -0.1700
Data Index: 5026025 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.8106. Min Act: -0.1700
Data Index: 1553673 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.8106. Min Act: -0.1700
Data Index: 5746483 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.7950. Min Act: -0.1700
Data Index: 3324081 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.7637. Min Act: -0.1700
Data Index: 2298560 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.7324. Min Act: -0.1700
Data Index: 8089004 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.7324. Min Act: -0.1700
Data Index: 668689 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.7011. Min Act: -0.1700
Data Index: 8341410 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6855. Min Act: -0.1700
Data Index: 4314388 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6855. Min Act: -0.1700
Data Index: 6643460 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6855. Min Act: -0.1700
Data Index: 3924427 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6698. Min Act: -0.1700
Data Index: 7786654 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6855. Min Act: -0.1700
Data Index: 1210618 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6698. Min Act: -0.1700
Data Index: 488184 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6698. Min Act: -0.1700
Data Index: 6543358 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0920. Min Range: -4.0920
Max Act: 3.6698. Min Act: -0.1700
Data Index: 792352 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19