Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3892. Min Act: -0.1700
Data Index: 3357398 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3892. Min Act: -0.1700
Data Index: 6619498 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3267. Min Act: -0.1700
Data Index: 1703654 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3580. Min Act: -0.1700
Data Index: 1926737 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3580. Min Act: -0.1700
Data Index: 1450078 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3267. Min Act: -0.1700
Data Index: 6818261 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.3267. Min Act: -0.1700
Data Index: 1450069 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2955. Min Act: -0.1700
Data Index: 5478495 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2955. Min Act: -0.1700
Data Index: 6619501 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4776075 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 57001 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2955. Min Act: -0.1700
Data Index: 1510937 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2955. Min Act: -0.1700
Data Index: 2824464 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2955. Min Act: -0.1700
Data Index: 8333264 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 1272342 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2330. Min Act: -0.1700
Data Index: 928682 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 3359572 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 936923 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4274944 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3892. Min Range: -5.3892
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4636367 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19