Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4532 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.4946. Min Act: -0.1700
Data Index: 3525225 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.4321. Min Act: -0.1700
Data Index: 8034250 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.3696. Min Act: -0.1700
Data Index: 5052646 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.3071. Min Act: -0.1700
Data Index: 5652745 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.2758. Min Act: -0.1700
Data Index: 3115745 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.2133. Min Act: -0.1700
Data Index: 1755550 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.1821. Min Act: -0.1700
Data Index: 6939221 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.1821. Min Act: -0.1700
Data Index: 7401895 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.1196. Min Act: -0.1700
Data Index: 7164656 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.1508. Min Act: -0.1700
Data Index: 1561351 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.0883. Min Act: -0.1700
Data Index: 7064970 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.0883. Min Act: -0.1700
Data Index: 5190022 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.0883. Min Act: -0.1700
Data Index: 3076565 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.0258. Min Act: -0.1700
Data Index: 7003937 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.0258. Min Act: -0.1700
Data Index: 6923773 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4946. Min Range: -6.4946
Max Act: 6.0258. Min Act: -0.1700
Data Index: 7096924 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4946. Min Range: -6.4946
Max Act: 5.9633. Min Act: -0.1700
Data Index: 120531 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4946. Min Range: -6.4946
Max Act: 5.9946. Min Act: -0.1700
Data Index: 4402117 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4946. Min Range: -6.4946
Max Act: 5.9946. Min Act: -0.1700
Data Index: 3993099 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4946. Min Range: -6.4946
Max Act: 5.9946. Min Act: -0.1700
Data Index: 26286 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19