Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.5573. Min Act: -0.1700
Data Index: 3525646 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4948. Min Act: -0.1700
Data Index: 967957 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.5260. Min Act: -0.1700
Data Index: 2404917 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4948. Min Act: -0.1700
Data Index: 1337588 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4323. Min Act: -0.1700
Data Index: 4634192 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4323. Min Act: -0.1700
Data Index: 6977088 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4010. Min Act: -0.1700
Data Index: 178375 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4010. Min Act: -0.1700
Data Index: 6380857 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4010. Min Act: -0.1700
Data Index: 8023756 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.4010. Min Act: -0.1700
Data Index: 4231630 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3698. Min Act: -0.1700
Data Index: 156028 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3698. Min Act: -0.1700
Data Index: 500277 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3698. Min Act: -0.1700
Data Index: 6307155 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3385. Min Act: -0.1700
Data Index: 268572 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3073. Min Act: -0.1700
Data Index: 2564860 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3073. Min Act: -0.1700
Data Index: 2591267 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3385. Min Act: -0.1700
Data Index: 6095645 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3073. Min Act: -0.1700
Data Index: 5754937 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.3073. Min Act: -0.1700
Data Index: 2191446 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5573. Min Range: -5.5573
Max Act: 5.2760. Min Act: -0.1700
Data Index: 4703526 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19