Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 785 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.6318. Min Act: -0.1700
Data Index: 676572 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.3193. Min Act: -0.1700
Data Index: 3008952 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.2568. Min Act: -0.1700
Data Index: 3008954 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3008966 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3008951 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.1943. Min Act: -0.1700
Data Index: 3008942 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.2255. Min Act: -0.1700
Data Index: 3008945 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 3008950 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.1005. Min Act: -0.1700
Data Index: 3008962 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.1005. Min Act: -0.1700
Data Index: 6248937 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 3008965 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3008953 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3008959 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 6445558 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.0380. Min Act: -0.1700
Data Index: 3008946 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.0380. Min Act: -0.1700
Data Index: 2102270 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6318. Min Range: -5.6318
Max Act: 4.9755. Min Act: -0.1700
Data Index: 4553831 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6318. Min Range: -5.6318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 3008943 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6318. Min Range: -5.6318
Max Act: 4.9755. Min Act: -0.1700
Data Index: 3008956 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6318. Min Range: -5.6318
Max Act: 4.9755. Min Act: -0.1700
Data Index: 4423683 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19