Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0465. Min Range: -5.0465
Max Act: 5.0465. Min Act: -0.1700
Data Index: 926511 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0465. Min Range: -5.0465
Max Act: 5.0465. Min Act: -0.1700
Data Index: 961966 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0465. Min Range: -5.0465
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5159120 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.9215. Min Act: -0.1700
Data Index: 6182796 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.8902. Min Act: -0.1700
Data Index: 39607 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.7965. Min Act: -0.1700
Data Index: 3891519 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.8277. Min Act: -0.1700
Data Index: 1106471 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.7652. Min Act: -0.1700
Data Index: 6829538 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.7652. Min Act: -0.1700
Data Index: 101396 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.7340. Min Act: -0.1700
Data Index: 3663944 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.6715. Min Act: -0.1700
Data Index: 4865559 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.6402. Min Act: -0.1700
Data Index: 2339242 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.6402. Min Act: -0.1700
Data Index: 7455208 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5777. Min Act: -0.1700
Data Index: 4973985 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5777. Min Act: -0.1700
Data Index: 238952 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5777. Min Act: -0.1700
Data Index: 4532596 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5777. Min Act: -0.1700
Data Index: 8817299 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5465. Min Act: -0.1700
Data Index: 4245583 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5465. Min Act: -0.1700
Data Index: 8589407 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0465. Min Range: -5.0465
Max Act: 4.5777. Min Act: -0.1700
Data Index: 7751052 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19