Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.8026. Min Act: -0.1700
Data Index: 6352184 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.6776. Min Act: -0.1700
Data Index: 7313342 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.7088. Min Act: -0.1700
Data Index: 6758826 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.6776. Min Act: -0.1700
Data Index: 2192924 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.6463. Min Act: -0.1700
Data Index: 976083 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.6151. Min Act: -0.1700
Data Index: 112539 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.6151. Min Act: -0.1700
Data Index: 4591922 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5838. Min Act: -0.1700
Data Index: 1805599 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5526. Min Act: -0.1700
Data Index: 5879712 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5526. Min Act: -0.1700
Data Index: 3643427 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5213. Min Act: -0.1700
Data Index: 1332357 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.4901. Min Act: -0.1700
Data Index: 8505267 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5213. Min Act: -0.1700
Data Index: 785053 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5213. Min Act: -0.1700
Data Index: 3083179 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.4901. Min Act: -0.1700
Data Index: 1518800 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.5213. Min Act: -0.1700
Data Index: 367326 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.4901. Min Act: -0.1700
Data Index: 3987649 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.4901. Min Act: -0.1700
Data Index: 6077507 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.4901. Min Act: -0.1700
Data Index: 3292310 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8026. Min Range: -4.8026
Max Act: 4.4276. Min Act: -0.1700
Data Index: 3623182 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19