Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0983. Min Range: -3.0983
Max Act: 3.0983. Min Act: -0.1700
Data Index: 2639853 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.9562. Min Act: -0.1700
Data Index: 1550990 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.9245. Min Act: -0.1700
Data Index: 7683176 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.9245. Min Act: -0.1700
Data Index: 4338714 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8928. Min Act: -0.1700
Data Index: 2580885 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8769. Min Act: -0.1700
Data Index: 1488441 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8769. Min Act: -0.1700
Data Index: 3399374 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8769. Min Act: -0.1700
Data Index: 8069985 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8769. Min Act: -0.1700
Data Index: 786279 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8293. Min Act: -0.1700
Data Index: 4630378 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8133. Min Act: -0.1700
Data Index: 2142773 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8293. Min Act: -0.1700
Data Index: 1858445 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.8133. Min Act: -0.1700
Data Index: 7592160 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7974. Min Act: -0.1700
Data Index: 3731157 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7974. Min Act: -0.1700
Data Index: 2598650 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7656. Min Act: -0.1700
Data Index: 4158233 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7815. Min Act: -0.1700
Data Index: 2005264 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7815. Min Act: -0.1700
Data Index: 5344263 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7656. Min Act: -0.1700
Data Index: 5850075 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0983. Min Range: -3.0983
Max Act: 2.7496. Min Act: -0.1700
Data Index: 482570 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19