Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 934173 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 2822064 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 758948 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 197441 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 8074996 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 550494 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 7699863 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1980. Min Act: -0.1700
Data Index: 5843222 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1668. Min Act: -0.1700
Data Index: 3908119 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1668. Min Act: -0.1700
Data Index: 4060331 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1980. Min Act: -0.1700
Data Index: 8695157 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1668. Min Act: -0.1700
Data Index: 8446485 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1668. Min Act: -0.1700
Data Index: 5279864 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1355. Min Act: -0.1700
Data Index: 3414666 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1043. Min Act: -0.1700
Data Index: 4780715 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1043. Min Act: -0.1700
Data Index: 648621 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1043. Min Act: -0.1700
Data Index: 2519200 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.0730. Min Act: -0.1700
Data Index: 6161579 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.1043. Min Act: -0.1700
Data Index: 397697 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2605. Min Range: -6.2605
Max Act: 6.0730. Min Act: -0.1700
Data Index: 4396070 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19