Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2409 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5543. Min Range: -9.5543
Max Act: 9.5543. Min Act: -0.1700
Data Index: 5755877 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5543. Min Range: -9.5543
Max Act: 9.4918. Min Act: -0.1700
Data Index: 1389802 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5543. Min Range: -9.5543
Max Act: 9.1793. Min Act: -0.1700
Data Index: 3392281 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5543. Min Range: -9.5543
Max Act: 9.1168. Min Act: -0.1700
Data Index: 3392280 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.8043. Min Act: -0.1700
Data Index: 4078005 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.8043. Min Act: -0.1700
Data Index: 5048304 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.6168. Min Act: -0.1700
Data Index: 5755878 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.5543. Min Act: -0.1700
Data Index: 4826049 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.5543. Min Act: -0.1700
Data Index: 6594883 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.5543. Min Act: -0.1700
Data Index: 6594878 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.4293. Min Act: -0.1700
Data Index: 8270957 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.4293. Min Act: -0.1700
Data Index: 4886389 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.3668. Min Act: -0.1700
Data Index: 3767028 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.3668. Min Act: -0.1700
Data Index: 759768 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.2418. Min Act: -0.1700
Data Index: 4528261 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.3043. Min Act: -0.1700
Data Index: 4461547 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.2106. Min Act: -0.1700
Data Index: 8672495 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.2418. Min Act: -0.1700
Data Index: 4978039 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.2418. Min Act: -0.1700
Data Index: 1541300 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5543. Min Range: -9.5543
Max Act: 8.1168. Min Act: -0.1700
Data Index: 6594881 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19