Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5976 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2037. Min Range: -6.2037
Max Act: 6.2037. Min Act: -0.1700
Data Index: 3431957 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2037. Min Range: -6.2037
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7970306 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2037. Min Range: -6.2037
Max Act: 6.0162. Min Act: -0.1700
Data Index: 5779557 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9849. Min Act: -0.1700
Data Index: 142858 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9537. Min Act: -0.1700
Data Index: 2963190 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9537. Min Act: -0.1700
Data Index: 466586 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9849. Min Act: -0.1700
Data Index: 6280589 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3896636 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9224. Min Act: -0.1700
Data Index: 5092512 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.8912. Min Act: -0.1700
Data Index: 6871212 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.9224. Min Act: -0.1700
Data Index: 626889 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.8912. Min Act: -0.1700
Data Index: 3020970 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.8912. Min Act: -0.1700
Data Index: 7380657 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.8287. Min Act: -0.1700
Data Index: 4347377 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.8287. Min Act: -0.1700
Data Index: 2940715 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7974. Min Act: -0.1700
Data Index: 7250198 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7974. Min Act: -0.1700
Data Index: 3567626 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7974. Min Act: -0.1700
Data Index: 227546 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7662. Min Act: -0.1700
Data Index: 7153036 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2037. Min Range: -6.2037
Max Act: 5.7662. Min Act: -0.1700
Data Index: 187269 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19