Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.5215. Min Act: -0.1700
Data Index: 8722485 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.5058. Min Act: -0.1700
Data Index: 1097010 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.4902. Min Act: -0.1700
Data Index: 4873772 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.4745. Min Act: -0.1700
Data Index: 2318257 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.4432. Min Act: -0.1700
Data Index: 8582394 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3962. Min Act: -0.1700
Data Index: 2736945 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3648. Min Act: -0.1700
Data Index: 5988196 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3648. Min Act: -0.1700
Data Index: 3039958 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3491. Min Act: -0.1700
Data Index: 2999431 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3491. Min Act: -0.1700
Data Index: 3580068 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3491. Min Act: -0.1700
Data Index: 2341406 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3334. Min Act: -0.1700
Data Index: 6678186 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3177. Min Act: -0.1700
Data Index: 299719 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3177. Min Act: -0.1700
Data Index: 3451276 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.3020. Min Act: -0.1700
Data Index: 3926809 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.2863. Min Act: -0.1700
Data Index: 8718035 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.2706. Min Act: -0.1700
Data Index: 7065872 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.2863. Min Act: -0.1700
Data Index: 767300 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.2863. Min Act: -0.1700
Data Index: 8300284 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5215. Min Range: -3.5215
Max Act: 3.2706. Min Act: -0.1700
Data Index: 7931187 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19