Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1095. Min Range: -7.1095
Max Act: 7.1095. Min Act: -0.1700
Data Index: 4789170 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1095. Min Range: -7.1095
Max Act: 7.1095. Min Act: -0.1700
Data Index: 5099200 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1095. Min Range: -7.1095
Max Act: 7.0470. Min Act: -0.1700
Data Index: 2335257 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.9533. Min Act: -0.1700
Data Index: 5230543 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.9220. Min Act: -0.1700
Data Index: 5028716 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.9220. Min Act: -0.1700
Data Index: 2274374 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.8908. Min Act: -0.1700
Data Index: 5819506 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7970. Min Act: -0.1700
Data Index: 510093 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7970. Min Act: -0.1700
Data Index: 3252898 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7658. Min Act: -0.1700
Data Index: 4184744 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7658. Min Act: -0.1700
Data Index: 2356337 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7345. Min Act: -0.1700
Data Index: 1923111 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7345. Min Act: -0.1700
Data Index: 8490743 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7345. Min Act: -0.1700
Data Index: 7066291 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7345. Min Act: -0.1700
Data Index: 42002 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.6720. Min Act: -0.1700
Data Index: 1937222 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7033. Min Act: -0.1700
Data Index: 8605559 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.7345. Min Act: -0.1700
Data Index: 378728 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.6720. Min Act: -0.1700
Data Index: 5915056 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1095. Min Range: -7.1095
Max Act: 6.6408. Min Act: -0.1700
Data Index: 5642496 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19