Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.5088. Min Act: -0.1700
Data Index: 1236531 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.4463. Min Act: -0.1700
Data Index: 8803112 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.2588. Min Act: -0.1700
Data Index: 235114 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 4207048 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.3213. Min Act: -0.1700
Data Index: 5755883 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.2588. Min Act: -0.1700
Data Index: 7546216 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 1511324 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 150170 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1338. Min Act: -0.1700
Data Index: 855763 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 344064 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 6966748 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 1820334 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 4121566 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 842917 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.0713. Min Act: -0.1700
Data Index: 1706936 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1338. Min Act: -0.1700
Data Index: 3107802 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1338. Min Act: -0.1700
Data Index: 916204 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1338. Min Act: -0.1700
Data Index: 306898 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1963. Min Act: -0.1700
Data Index: 3115433 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5088. Min Range: -9.5088
Max Act: 9.1338. Min Act: -0.1700
Data Index: 1023179 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19