Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 499 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.8177. Min Act: -0.1700
Data Index: 1845517 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.8177. Min Act: -0.1700
Data Index: 8670468 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.7552. Min Act: -0.1700
Data Index: 6925790 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.7240. Min Act: -0.1700
Data Index: 1890113 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.7240. Min Act: -0.1700
Data Index: 8416446 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.6927. Min Act: -0.1700
Data Index: 4391816 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.6927. Min Act: -0.1700
Data Index: 5425174 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.6615. Min Act: -0.1700
Data Index: 2908919 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.6615. Min Act: -0.1700
Data Index: 5476321 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.6615. Min Act: -0.1700
Data Index: 5329185 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5990. Min Act: -0.1700
Data Index: 7019844 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.6615. Min Act: -0.1700
Data Index: 4392119 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5677. Min Act: -0.1700
Data Index: 3910345 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5677. Min Act: -0.1700
Data Index: 7562128 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5990. Min Act: -0.1700
Data Index: 448 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5677. Min Act: -0.1700
Data Index: 3064382 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5677. Min Act: -0.1700
Data Index: 426351 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5365. Min Act: -0.1700
Data Index: 2973897 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5677. Min Act: -0.1700
Data Index: 5463026 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8177. Min Range: -4.8177
Max Act: 4.5365. Min Act: -0.1700
Data Index: 1898739 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19