Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 89 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.5020. Min Act: -0.1700
Data Index: 1272133 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.4708. Min Act: -0.1700
Data Index: 1187993 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.4395. Min Act: -0.1700
Data Index: 6169600 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.4083. Min Act: -0.1700
Data Index: 462702 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.4083. Min Act: -0.1700
Data Index: 5277013 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.3458. Min Act: -0.1700
Data Index: 85654 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.4083. Min Act: -0.1700
Data Index: 6532089 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.3458. Min Act: -0.1700
Data Index: 740460 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.3145. Min Act: -0.1700
Data Index: 8229439 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.3145. Min Act: -0.1700
Data Index: 7382941 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.3458. Min Act: -0.1700
Data Index: 8331092 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.3145. Min Act: -0.1700
Data Index: 1212436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2833. Min Act: -0.1700
Data Index: 5746103 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2520. Min Act: -0.1700
Data Index: 3685118 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2520. Min Act: -0.1700
Data Index: 2937846 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2520. Min Act: -0.1700
Data Index: 5652022 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2833. Min Act: -0.1700
Data Index: 8386840 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2520. Min Act: -0.1700
Data Index: 8508225 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2208. Min Act: -0.1700
Data Index: 3366466 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5020. Min Range: -4.5020
Max Act: 4.2208. Min Act: -0.1700
Data Index: 7196332 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19