Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.2654. Min Act: -0.1700
Data Index: 1017322 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.2324. Min Act: -0.1700
Data Index: 5906953 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1993. Min Act: -0.1700
Data Index: 5211606 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.2158. Min Act: -0.1700
Data Index: 8523235 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1993. Min Act: -0.1700
Data Index: 3977643 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1993. Min Act: -0.1700
Data Index: 2813019 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1826. Min Act: -0.1700
Data Index: 4017072 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1660. Min Act: -0.1700
Data Index: 1484639 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 6242807 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1494. Min Act: -0.1700
Data Index: 8119371 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1494. Min Act: -0.1700
Data Index: 2550143 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1494. Min Act: -0.1700
Data Index: 3245214 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 3319943 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1494. Min Act: -0.1700
Data Index: 4877012 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 5970172 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 4839396 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 7310639 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 154672 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 5571772 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2654. Min Range: -2.2654
Max Act: 2.1327. Min Act: -0.1700
Data Index: 2171091 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19