Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0547. Min Range: -6.0547
Max Act: 6.0547. Min Act: -0.1700
Data Index: 2579223 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4610. Min Act: -0.1700
Data Index: 3317830 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4610. Min Act: -0.1700
Data Index: 4548910 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4922. Min Act: -0.1700
Data Index: 1258542 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4610. Min Act: -0.1700
Data Index: 8386367 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4610. Min Act: -0.1700
Data Index: 8332852 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4610. Min Act: -0.1700
Data Index: 3383654 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.4297. Min Act: -0.1700
Data Index: 7930528 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.3360. Min Act: -0.1700
Data Index: 5512859 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.2422. Min Act: -0.1700
Data Index: 2123242 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.2422. Min Act: -0.1700
Data Index: 152661 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.2110. Min Act: -0.1700
Data Index: 372579 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.2110. Min Act: -0.1700
Data Index: 6237048 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.1797. Min Act: -0.1700
Data Index: 7997708 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.2110. Min Act: -0.1700
Data Index: 5911567 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.1797. Min Act: -0.1700
Data Index: 8237879 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.1797. Min Act: -0.1700
Data Index: 4587368 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.1485. Min Act: -0.1700
Data Index: 2192781 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.1485. Min Act: -0.1700
Data Index: 5313516 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0547. Min Range: -6.0547
Max Act: 5.1485. Min Act: -0.1700
Data Index: 5046053 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19