Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4671 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0356. Min Range: -6.0356
Max Act: 6.0356. Min Act: -0.1700
Data Index: 8496889 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.8481. Min Act: -0.1700
Data Index: 128905 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.7856. Min Act: -0.1700
Data Index: 2524710 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1799216 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5981. Min Act: -0.1700
Data Index: 2810143 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.6606. Min Act: -0.1700
Data Index: 666262 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5981. Min Act: -0.1700
Data Index: 1341683 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5981. Min Act: -0.1700
Data Index: 4335247 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.6293. Min Act: -0.1700
Data Index: 2837125 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5668. Min Act: -0.1700
Data Index: 261567 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5668. Min Act: -0.1700
Data Index: 422803 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5668. Min Act: -0.1700
Data Index: 4025377 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5668. Min Act: -0.1700
Data Index: 8290669 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5356. Min Act: -0.1700
Data Index: 1875887 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.5043. Min Act: -0.1700
Data Index: 3693465 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.4731. Min Act: -0.1700
Data Index: 4335257 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.4731. Min Act: -0.1700
Data Index: 1538726 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.4731. Min Act: -0.1700
Data Index: 405820 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.4418. Min Act: -0.1700
Data Index: 4800858 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0356. Min Range: -6.0356
Max Act: 5.4418. Min Act: -0.1700
Data Index: 2603958 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19