Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.6931. Min Act: -0.1700
Data Index: 5978146 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5807. Min Act: -0.1700
Data Index: 5580510 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5968. Min Act: -0.1700
Data Index: 140554 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5807. Min Act: -0.1700
Data Index: 8191061 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5484. Min Act: -0.1700
Data Index: 7516028 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5484. Min Act: -0.1700
Data Index: 3891093 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5323. Min Act: -0.1700
Data Index: 6417898 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5323. Min Act: -0.1700
Data Index: 8150295 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5161. Min Act: -0.1700
Data Index: 5489713 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5161. Min Act: -0.1700
Data Index: 397375 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.5161. Min Act: -0.1700
Data Index: 543555 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4999. Min Act: -0.1700
Data Index: 2261901 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4999. Min Act: -0.1700
Data Index: 894432 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4999. Min Act: -0.1700
Data Index: 8020267 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4999. Min Act: -0.1700
Data Index: 4413550 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4837. Min Act: -0.1700
Data Index: 104315 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4837. Min Act: -0.1700
Data Index: 2148483 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4837. Min Act: -0.1700
Data Index: 8542924 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4837. Min Act: -0.1700
Data Index: 137635 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6931. Min Range: -2.6931
Max Act: 2.4675. Min Act: -0.1700
Data Index: 1860521 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19