Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.4103. Min Act: -0.1700
Data Index: 8453563 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.3791. Min Act: -0.1700
Data Index: 441292 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.3478. Min Act: -0.1700
Data Index: 2599873 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2853. Min Act: -0.1700
Data Index: 1772754 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6104642 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 53488 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 2620263 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 12178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 5271317 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 2563040 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 2728599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.1916. Min Act: -0.1700
Data Index: 920145 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 7416479 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 54941 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 1876309 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 940515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 3016043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 2307336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.1916. Min Act: -0.1700
Data Index: 5116092 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4103. Min Range: -5.4103
Max Act: 5.1603. Min Act: -0.1700
Data Index: 2810324 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19