Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5795 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.3788. Min Act: -0.1700
Data Index: 4074680 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.3163. Min Act: -0.1700
Data Index: 490863 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.2851. Min Act: -0.1700
Data Index: 2594815 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.1913. Min Act: -0.1700
Data Index: 8469868 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4276858 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.1601. Min Act: -0.1700
Data Index: 2637445 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.1601. Min Act: -0.1700
Data Index: 7294461 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.1288. Min Act: -0.1700
Data Index: 2036584 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.1288. Min Act: -0.1700
Data Index: 2047403 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0976. Min Act: -0.1700
Data Index: 7924613 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0976. Min Act: -0.1700
Data Index: 1745714 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0976. Min Act: -0.1700
Data Index: 4190358 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0663. Min Act: -0.1700
Data Index: 4489193 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0351. Min Act: -0.1700
Data Index: 3540653 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0351. Min Act: -0.1700
Data Index: 3354495 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0351. Min Act: -0.1700
Data Index: 3318072 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0038. Min Act: -0.1700
Data Index: 5684718 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0038. Min Act: -0.1700
Data Index: 1277608 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0038. Min Act: -0.1700
Data Index: 5212762 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3788. Min Range: -6.3788
Max Act: 6.0351. Min Act: -0.1700
Data Index: 214805 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19