Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2029 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.5181. Min Act: -0.1700
Data Index: 6142346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4830. Min Act: -0.1700
Data Index: 7125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4655. Min Act: -0.1700
Data Index: 6942673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4655. Min Act: -0.1700
Data Index: 711534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4567. Min Act: -0.1699
Data Index: 2922439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4479. Min Act: -0.1700
Data Index: 7464123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4303. Min Act: -0.1700
Data Index: 6282260 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4215. Min Act: -0.1700
Data Index: 57038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4303. Min Act: -0.1700
Data Index: 6531066 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4215. Min Act: -0.1700
Data Index: 7480647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4127. Min Act: -0.1700
Data Index: 696337 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4038. Min Act: -0.1700
Data Index: 1015702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3950. Min Act: -0.1700
Data Index: 6557339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3950. Min Act: -0.1699
Data Index: 6654158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.4038. Min Act: -0.1700
Data Index: 2454073 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3774. Min Act: -0.1700
Data Index: 3042932 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3862. Min Act: -0.1700
Data Index: 4636624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3862. Min Act: -0.1700
Data Index: 5865495 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3774. Min Act: -0.1700
Data Index: 4007488 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5181. Min Range: -1.5181
Max Act: 1.3774. Min Act: -0.1691
Data Index: 7969430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19