Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2199 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.9436. Min Act: -0.1700
Data Index: 1801048 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6934. Min Act: -0.1700
Data Index: 2125866 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6465. Min Act: -0.1700
Data Index: 5687918 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6465. Min Act: -0.1700
Data Index: 255576 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6465. Min Act: -0.1700
Data Index: 3186558 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6152. Min Act: -0.1700
Data Index: 6194163 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5682. Min Act: -0.1700
Data Index: 1087927 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5525. Min Act: -0.1700
Data Index: 6726316 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5212. Min Act: -0.1700
Data Index: 1838892 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5369. Min Act: -0.1700
Data Index: 7289066 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5212. Min Act: -0.1700
Data Index: 3906334 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5212. Min Act: -0.1700
Data Index: 8665392 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5212. Min Act: -0.1700
Data Index: 5907666 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5056. Min Act: -0.1700
Data Index: 5682183 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.4899. Min Act: -0.1700
Data Index: 4814014 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.4742. Min Act: -0.1700
Data Index: 1113403 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.4742. Min Act: -0.1700
Data Index: 4925722 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.4429. Min Act: -0.1700
Data Index: 1757939 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.4429. Min Act: -0.1700
Data Index: 1689244 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.4586. Min Act: -0.1700
Data Index: 3302415 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19