Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5213 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2951. Min Range: -8.2951
Max Act: 8.2951. Min Act: -0.1700
Data Index: 6562053 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2951. Min Range: -8.2951
Max Act: 8.1701. Min Act: -0.1700
Data Index: 6261040 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.9826. Min Act: -0.1700
Data Index: 8120436 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.9513. Min Act: -0.1700
Data Index: 2837149 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.9201. Min Act: -0.1700
Data Index: 2992131 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.8263. Min Act: -0.1700
Data Index: 3131383 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.8263. Min Act: -0.1700
Data Index: 1371694 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.7013. Min Act: -0.1700
Data Index: 5652561 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.6076. Min Act: -0.1700
Data Index: 2448407 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.5451. Min Act: -0.1700
Data Index: 831979 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4826. Min Act: -0.1700
Data Index: 7534433 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.5138. Min Act: -0.1700
Data Index: 4439520 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4826. Min Act: -0.1700
Data Index: 7058367 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4513. Min Act: -0.1700
Data Index: 5783269 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4826. Min Act: -0.1700
Data Index: 7323047 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4826. Min Act: -0.1700
Data Index: 97778 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4826. Min Act: -0.1700
Data Index: 7462410 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.4201. Min Act: -0.1700
Data Index: 4383223 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.3888. Min Act: -0.1700
Data Index: 6285922 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2951. Min Range: -8.2951
Max Act: 7.3888. Min Act: -0.1700
Data Index: 3080589 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19