Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 65 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3151. Min Range: -6.3151
Max Act: 6.3151. Min Act: -0.1700
Data Index: 1716897 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3151. Min Range: -6.3151
Max Act: 6.1588. Min Act: -0.1700
Data Index: 4070690 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3151. Min Range: -6.3151
Max Act: 6.0026. Min Act: -0.1700
Data Index: 4677617 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3151. Min Range: -6.3151
Max Act: 6.0026. Min Act: -0.1700
Data Index: 1244082 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.9713. Min Act: -0.1700
Data Index: 181689 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.9088. Min Act: -0.1700
Data Index: 5766454 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.9401. Min Act: -0.1700
Data Index: 2394701 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.9088. Min Act: -0.1700
Data Index: 5898621 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8463. Min Act: -0.1700
Data Index: 7620894 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8463. Min Act: -0.1700
Data Index: 6187509 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8463. Min Act: -0.1700
Data Index: 7311350 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8151. Min Act: -0.1700
Data Index: 220118 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8151. Min Act: -0.1700
Data Index: 8664463 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8151. Min Act: -0.1700
Data Index: 7338675 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.7838. Min Act: -0.1700
Data Index: 7528980 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.7838. Min Act: -0.1700
Data Index: 1819060 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.7838. Min Act: -0.1700
Data Index: 8329791 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.7838. Min Act: -0.1700
Data Index: 144319 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.8151. Min Act: -0.1700
Data Index: 7876219 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3151. Min Range: -6.3151
Max Act: 5.7838. Min Act: -0.1700
Data Index: 4388512 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19