Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1626. Min Range: -2.1626
Max Act: 2.1626. Min Act: -0.1700
Data Index: 8457426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1626. Min Range: -2.1626
Max Act: 2.0958. Min Act: -0.1700
Data Index: 2770445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9948. Min Act: -0.1700
Data Index: 2075544 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9269. Min Act: -0.1700
Data Index: 1944915 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9269. Min Act: -0.1700
Data Index: 6632904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9269. Min Act: -0.1700
Data Index: 6010910 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9269. Min Act: -0.1700
Data Index: 4644266 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8929. Min Act: -0.1700
Data Index: 8193224 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9099. Min Act: -0.1700
Data Index: 3335970 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9099. Min Act: -0.1700
Data Index: 1066109 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9269. Min Act: -0.1700
Data Index: 1740770 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9099. Min Act: -0.1700
Data Index: 2632870 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9099. Min Act: -0.1700
Data Index: 3079194 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8929. Min Act: -0.1700
Data Index: 1978467 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8929. Min Act: -0.1700
Data Index: 4074514 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8929. Min Act: -0.1700
Data Index: 4974887 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.9099. Min Act: -0.1700
Data Index: 892551 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8758. Min Act: -0.1700
Data Index: 399086 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8758. Min Act: -0.1700
Data Index: 4293145 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1626. Min Range: -2.1626
Max Act: 1.8758. Min Act: -0.1700
Data Index: 6204716 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19