Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.4265. Min Act: -0.1700
Data Index: 3786354 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.3939. Min Act: -0.1700
Data Index: 3786355 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.3120. Min Act: -0.1700
Data Index: 1554530 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.2791. Min Act: -0.1700
Data Index: 8259580 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.2295. Min Act: -0.1700
Data Index: 302006 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.2295. Min Act: -0.1700
Data Index: 1054729 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.2130. Min Act: -0.1700
Data Index: 867375 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.2130. Min Act: -0.1700
Data Index: 6895271 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1964. Min Act: -0.1700
Data Index: 3786353 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1631. Min Act: -0.1700
Data Index: 8665972 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1465. Min Act: -0.1700
Data Index: 2611444 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1465. Min Act: -0.1700
Data Index: 7493869 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1298. Min Act: -0.1700
Data Index: 3699289 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1298. Min Act: -0.1700
Data Index: 2897315 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1465. Min Act: -0.1700
Data Index: 6007990 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1131. Min Act: -0.1700
Data Index: 673580 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1131. Min Act: -0.1700
Data Index: 7331462 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1131. Min Act: -0.1700
Data Index: 2565192 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.0963. Min Act: -0.1700
Data Index: 5540927 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4265. Min Range: -2.4265
Max Act: 2.1131. Min Act: -0.1700
Data Index: 4277489 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19