Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1627 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.4341. Min Act: -0.1700
Data Index: 7436970 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.4654. Min Act: -0.1700
Data Index: 4400211 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.2466. Min Act: -0.1700
Data Index: 1340524 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.1529. Min Act: -0.1700
Data Index: 3507293 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.1216. Min Act: -0.1700
Data Index: 2452136 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.1216. Min Act: -0.1700
Data Index: 2565128 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.1216. Min Act: -0.1700
Data Index: 4742557 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.1216. Min Act: -0.1700
Data Index: 8371050 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0904. Min Act: -0.1700
Data Index: 821059 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.1216. Min Act: -0.1700
Data Index: 3775358 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0904. Min Act: -0.1700
Data Index: 7772142 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0904. Min Act: -0.1700
Data Index: 1584289 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0591. Min Act: -0.1700
Data Index: 5194185 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0591. Min Act: -0.1700
Data Index: 6866104 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0904. Min Act: -0.1700
Data Index: 7271275 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0904. Min Act: -0.1700
Data Index: 8294125 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0591. Min Act: -0.1700
Data Index: 6738725 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0591. Min Act: -0.1700
Data Index: 541088 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0279. Min Act: -0.1700
Data Index: 880068 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4654. Min Range: -5.4654
Max Act: 5.0279. Min Act: -0.1700
Data Index: 6334964 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19