Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.9957. Min Act: -0.1700
Data Index: 1062188 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.8394. Min Act: -0.1700
Data Index: 4343171 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 4642759 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.8394. Min Act: -0.1700
Data Index: 2063508 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4188372 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7457. Min Act: -0.1700
Data Index: 8774510 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7769. Min Act: -0.1700
Data Index: 5904222 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7769. Min Act: -0.1700
Data Index: 783063 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 4038937 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 1576847 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7457. Min Act: -0.1700
Data Index: 8497315 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7457. Min Act: -0.1700
Data Index: 2376008 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 537229 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 7591359 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 5010723 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 6839018 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7457. Min Act: -0.1700
Data Index: 265081 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 6794008 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 1644730 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9957. Min Range: -4.9957
Max Act: 4.7144. Min Act: -0.1700
Data Index: 4430130 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19