Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4226. Min Range: -3.4226
Max Act: 3.4226. Min Act: -0.1700
Data Index: 3046535 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4226. Min Range: -3.4226
Max Act: 3.3442. Min Act: -0.1700
Data Index: 852192 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4226. Min Range: -3.4226
Max Act: 3.1714. Min Act: -0.1700
Data Index: 2272030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4226. Min Range: -3.4226
Max Act: 3.1084. Min Act: -0.1700
Data Index: 2634156 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4226. Min Range: -3.4226
Max Act: 3.0138. Min Act: -0.1700
Data Index: 1221285 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9347. Min Act: -0.1700
Data Index: 7898100 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9505. Min Act: -0.1700
Data Index: 6497534 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9347. Min Act: -0.1700
Data Index: 3810053 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9030. Min Act: -0.1700
Data Index: 4951724 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9030. Min Act: -0.1700
Data Index: 523824 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9030. Min Act: -0.1700
Data Index: 5831842 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8871. Min Act: -0.1700
Data Index: 8376574 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8713. Min Act: -0.1700
Data Index: 4420728 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.9030. Min Act: -0.1700
Data Index: 5157284 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8871. Min Act: -0.1700
Data Index: 7266904 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8713. Min Act: -0.1700
Data Index: 1536656 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8554. Min Act: -0.1700
Data Index: 5326454 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8554. Min Act: -0.1700
Data Index: 7355632 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8554. Min Act: -0.1700
Data Index: 1488809 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4226. Min Range: -3.4226
Max Act: 2.8554. Min Act: -0.1700
Data Index: 1345342 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19