Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4101. Min Range: -8.4101
Max Act: 8.4101. Min Act: -0.1700
Data Index: 5013366 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4101. Min Range: -8.4101
Max Act: 8.0976. Min Act: -0.1700
Data Index: 6185591 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4101. Min Range: -8.4101
Max Act: 8.0663. Min Act: -0.1700
Data Index: 3629575 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.6913. Min Act: -0.1700
Data Index: 4297334 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.5663. Min Act: -0.1700
Data Index: 2996890 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.5663. Min Act: -0.1700
Data Index: 619792 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5792908 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.5038. Min Act: -0.1700
Data Index: 7753109 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.5038. Min Act: -0.1700
Data Index: 7988285 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.3788. Min Act: -0.1700
Data Index: 4531476 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.3788. Min Act: -0.1700
Data Index: 1916875 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.4101. Min Act: -0.1700
Data Index: 7157571 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.3163. Min Act: -0.1700
Data Index: 3884414 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.2538. Min Act: -0.1700
Data Index: 675309 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.2851. Min Act: -0.1700
Data Index: 6214461 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.2538. Min Act: -0.1700
Data Index: 3628619 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.2226. Min Act: -0.1700
Data Index: 5969375 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.1913. Min Act: -0.1700
Data Index: 4827565 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.1913. Min Act: -0.1700
Data Index: 6091347 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4101. Min Range: -8.4101
Max Act: 7.1601. Min Act: -0.1700
Data Index: 3827802 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19