Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.5652. Min Act: -0.1700
Data Index: 3501774 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.5340. Min Act: -0.1700
Data Index: 8446915 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.5340. Min Act: -0.1700
Data Index: 1556052 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.5340. Min Act: -0.1700
Data Index: 8768685 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4715. Min Act: -0.1700
Data Index: 5356425 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4715. Min Act: -0.1700
Data Index: 1628501 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4402. Min Act: -0.1700
Data Index: 702101 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4402. Min Act: -0.1700
Data Index: 295394 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4402. Min Act: -0.1700
Data Index: 5733221 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4402. Min Act: -0.1700
Data Index: 3370376 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4090. Min Act: -0.1700
Data Index: 5403363 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4090. Min Act: -0.1700
Data Index: 3966410 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.4090. Min Act: -0.1700
Data Index: 7819010 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 7814151 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 3847818 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 4593380 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 5026212 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 4218249 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 7824375 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5652. Min Range: -4.5652
Max Act: 4.3777. Min Act: -0.1700
Data Index: 4502254 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19