Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4126 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4408. Min Range: -7.4408
Max Act: 7.4408. Min Act: -0.1700
Data Index: 2465682 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4408. Min Range: -7.4408
Max Act: 7.3783. Min Act: -0.1700
Data Index: 7356092 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4408. Min Range: -7.4408
Max Act: 7.2221. Min Act: -0.1700
Data Index: 238738 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4408. Min Range: -7.4408
Max Act: 7.2221. Min Act: -0.1700
Data Index: 6145742 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4408. Min Range: -7.4408
Max Act: 7.0033. Min Act: -0.1700
Data Index: 7680763 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9721. Min Act: -0.1700
Data Index: 5095412 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9721. Min Act: -0.1700
Data Index: 5368460 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9721. Min Act: -0.1700
Data Index: 5462662 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9721. Min Act: -0.1700
Data Index: 568190 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9408. Min Act: -0.1700
Data Index: 3760355 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9096. Min Act: -0.1700
Data Index: 7604578 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.9096. Min Act: -0.1700
Data Index: 3409307 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8783. Min Act: -0.1700
Data Index: 4714457 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8783. Min Act: -0.1700
Data Index: 2239810 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8471. Min Act: -0.1700
Data Index: 3764678 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8783. Min Act: -0.1700
Data Index: 3216153 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8471. Min Act: -0.1700
Data Index: 6111103 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8158. Min Act: -0.1700
Data Index: 6209019 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8471. Min Act: -0.1700
Data Index: 3992164 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4408. Min Range: -7.4408
Max Act: 6.8471. Min Act: -0.1700
Data Index: 5810503 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19