Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.2886. Min Act: -0.1700
Data Index: 696091 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.1636. Min Act: -0.1700
Data Index: 5883678 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9761. Min Act: -0.1700
Data Index: 8084367 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.0386. Min Act: -0.1700
Data Index: 1520654 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9761. Min Act: -0.1700
Data Index: 6861058 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9761. Min Act: -0.1700
Data Index: 1445664 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9136. Min Act: -0.1700
Data Index: 7063879 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9136. Min Act: -0.1700
Data Index: 7784455 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9136. Min Act: -0.1700
Data Index: 7823811 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.8511. Min Act: -0.1700
Data Index: 1722603 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7886. Min Act: -0.1700
Data Index: 4964067 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7886. Min Act: -0.1700
Data Index: 7181435 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7886. Min Act: -0.1700
Data Index: 5855904 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7886. Min Act: -0.1700
Data Index: 1836952 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7261. Min Act: -0.1700
Data Index: 5284048 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7261. Min Act: -0.1700
Data Index: 7932728 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7261. Min Act: -0.1700
Data Index: 8613228 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7261. Min Act: -0.1700
Data Index: 7666148 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7261. Min Act: -0.1700
Data Index: 3122014 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.7261. Min Act: -0.1700
Data Index: 8770295 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19