Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 795 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.4970. Min Act: -0.1700
Data Index: 8502873 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.4345. Min Act: -0.1700
Data Index: 2369365 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.4345. Min Act: -0.1700
Data Index: 6506494 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.4345. Min Act: -0.1700
Data Index: 1654316 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.4033. Min Act: -0.1700
Data Index: 6006399 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.3720. Min Act: -0.1700
Data Index: 7391689 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.3408. Min Act: -0.1700
Data Index: 5192099 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.3095. Min Act: -0.1700
Data Index: 5451797 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.3095. Min Act: -0.1700
Data Index: 3349115 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.3095. Min Act: -0.1700
Data Index: 6535178 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 2952984 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2783. Min Act: -0.1700
Data Index: 5192100 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2783. Min Act: -0.1700
Data Index: 6245732 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 4004776 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 8749145 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 7587210 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 2280754 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 3696167 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2158. Min Act: -0.1700
Data Index: 7108291 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4970. Min Range: -5.4970
Max Act: 5.2158. Min Act: -0.1700
Data Index: 158597 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19